From ec05b94b4267594b2bff72611b4d470591df6e81 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 28 Jul 2026 18:18:47 +0000 Subject: [PATCH 1/2] feat(requesty): add sync module for the Requesty catalog Co-Authored-By: john --- package.json | 1 + packages/core/src/sync/index.ts | 5 +- packages/core/src/sync/providers/requesty.ts | 219 +++++++++++++++++++ packages/core/test/sync.test.ts | 89 ++++++++ sync.md | 14 ++ 5 files changed, 327 insertions(+), 1 deletion(-) create mode 100644 packages/core/src/sync/providers/requesty.ts diff --git a/package.json b/package.json index d4cab62ded0..7f05742d50d 100644 --- a/package.json +++ b/package.json @@ -28,6 +28,7 @@ "huggingface:sync": "bun ./packages/core/script/sync-models.ts huggingface", "kilo:sync": "bun ./packages/core/script/sync-models.ts kilo", "llmgateway:sync": "bun ./packages/core/script/sync-models.ts llmgateway", + "requesty:sync": "bun ./packages/core/script/sync-models.ts requesty", "venice:sync": "bun ./packages/core/script/sync-models.ts venice", "vercel:generate": "bun ./packages/core/script/sync-models.ts vercel", "wandb:generate": "bun ./packages/core/script/sync-models.ts wandb", diff --git a/packages/core/src/sync/index.ts b/packages/core/src/sync/index.ts index e8e516708c2..52ac95c6af2 100644 --- a/packages/core/src/sync/index.ts +++ b/packages/core/src/sync/index.ts @@ -23,6 +23,7 @@ import { openai } from "./providers/openai.js"; import { openrouter } from "./providers/openrouter.js"; import { ovhcloud } from "./providers/ovhcloud.js"; import { pioneer } from "./providers/pioneer.js"; +import { requesty } from "./providers/requesty.js"; import { vercel } from "./providers/vercel.js"; import { venice } from "./providers/venice.js"; import { wandb } from "./providers/wandb.js"; @@ -123,6 +124,7 @@ export const providers: { openrouter: SyncProvider; ovhcloud: SyncProvider; pioneer: SyncProvider; + requesty: SyncProvider; vercel: SyncProvider; venice: SyncProvider; wandb: SyncProvider; @@ -146,6 +148,7 @@ export const providers: { openrouter, ovhcloud, pioneer, + requesty, vercel, venice, wandb, @@ -153,7 +156,7 @@ export const providers: { }; export const groups = { - aggregators: ["crossmodel", "empiriolabs", "huggingface", "kilo", "llmgateway", "openrouter", "vercel"], + aggregators: ["crossmodel", "empiriolabs", "huggingface", "kilo", "llmgateway", "openrouter", "requesty", "vercel"], cloudflare: ["cloudflare-workers-ai"], direct: ["ambient", "anthropic", "baseten", "chutes", "deepinfra", "digitalocean", "google", "hyper", "openai", "ovhcloud", "pioneer", "venice", "wandb", "xai"], } as const; diff --git a/packages/core/src/sync/providers/requesty.ts b/packages/core/src/sync/providers/requesty.ts new file mode 100644 index 00000000000..5640c1f0df5 --- /dev/null +++ b/packages/core/src/sync/providers/requesty.ts @@ -0,0 +1,219 @@ +import { readFileSync, readdirSync } from "node:fs"; +import path from "node:path"; + +import { z } from "zod"; + +import type { + ExistingModel, + SyncProvider, + SyncedBaseModel, + SyncedFullModel, + SyncedModel, +} from "../index.js"; +import { buildOpenRouterModel, type OpenRouterModel } from "./openrouter.js"; + +const API_ENDPOINT = "https://router.requesty.ai/v1/models"; +const MODELS_DIR = path.join(import.meta.dirname, "..", "..", "..", "..", "..", "models"); +const TOKENS_PER_MILLION = 1_000_000; +const PRICE_DECIMALS = 1_000_000; +const REASONING_EFFORTS = ["none", "low", "medium", "high", "max"] as const; + +const PricingBand = z + .object({ + prompt_tokens_threshold: z.number(), + input_price: z.number().optional(), + output_price: z.number().optional(), + cached_price: z.number().optional(), + caching_price: z.number().optional(), + }) + .passthrough(); + +export const RequestyModel = z + .object({ + id: z.string().min(1), + created: z.number(), + context_window: z.number(), + max_output_tokens: z.number(), + input_price: z.number(), + output_price: z.number(), + cached_price: z.number().optional(), + caching_price: z.number().optional(), + pricing: z.array(PricingBand).optional(), + supports_vision: z.boolean().optional(), + supports_reasoning: z.boolean().optional(), + supports_tool_calling: z.boolean().optional(), + supports_output_json_schema: z.boolean().optional(), + }) + .passthrough(); + +export const RequestyResponse = z + .object({ + object: z.literal("list"), + data: z.array(RequestyModel), + }) + .passthrough(); + +const BaseMetadata = z + .object({ + reasoning: z.boolean().optional(), + temperature: z.boolean().optional(), + tool_call: z.boolean().optional(), + structured_output: z.boolean().optional(), + open_weights: z.boolean().optional(), + limit: z.object({ context: z.number(), output: z.number().optional() }).passthrough(), + modalities: z + .object({ input: z.array(z.string()), output: z.array(z.string()) }) + .passthrough(), + }) + .passthrough(); + +export type RequestyModel = z.infer; +type BaseMetadata = z.infer; + +export const requesty = { + id: "requesty", + name: "Requesty", + modelsDir: "providers/requesty/models", + sourceID: (model) => model.id, + skippedNotice: (ids) => [ + `${ids.length} Requesty routes have no \`models/\` metadata entry yet: ${ids.join(", ")}`, + ], + async fetchModels() { + const response = await fetch(API_ENDPOINT); + if (!response.ok) { + throw new Error(`Requesty request failed: ${response.status} ${response.statusText}`); + } + return response.json(); + }, + parseModels(raw) { + return RequestyResponse.parse(raw).data; + }, + translateModel(model, context) { + const baseModel = resolveRequestyBaseModel(model.id); + // A route with no metadata to inherit keeps whatever is authored for it. + if (baseModel === undefined) { + const authored = context.authored(model.id); + return authored === undefined ? undefined : { id: model.id, model: authored as SyncedModel }; + } + return { + id: model.id, + model: buildRequestyModel(model, baseModel, context.existing(model.id)), + }; + }, +} satisfies SyncProvider; + +export function buildRequestyModel( + model: RequestyModel, + baseModel: string, + existing: ExistingModel | undefined, +): SyncedModel { + const base = baseMetadata(baseModel); + const built = buildOpenRouterModel( + toOpenRouterModel(model, base), + existing, + baseModel, + ) as SyncedBaseModel; + // Name, description, and family are provider-agnostic facts of the base model. + const { name: _name, description: _description, family: _family, ...factored } = built; + const tiers = pricingTiers(model) ?? existing?.cost?.tiers; + return tiers === undefined ? factored : { ...factored, cost: { ...factored.cost, tiers } }; +} + +function toOpenRouterModel(model: RequestyModel, base: BaseMetadata): OpenRouterModel { + const context = model.context_window > 0 ? model.context_window : base.limit.context; + const reasoning = model.supports_reasoning === true || base.reasoning === true; + return { + id: model.id, + name: "", + created: model.created, + hugging_face_id: base.open_weights === true ? model.id : null, + knowledge_cutoff: null, + context_length: context, + architecture: { + input_modalities: base.modalities.input, + output_modalities: base.modalities.output, + }, + pricing: { + prompt: String(model.input_price), + completion: String(model.output_price), + input_cache_read: chargedPerTokenPrice(model.cached_price), + input_cache_write: chargedPerTokenPrice(model.caching_price), + }, + top_provider: { + context_length: context, + max_completion_tokens: model.max_output_tokens > 0 + ? model.max_output_tokens + : base.limit.output ?? null, + }, + supported_parameters: [ + ...(base.temperature === false ? [] : ["temperature"]), + ...(reasoning ? ["reasoning"] : []), + ...(model.supports_tool_calling === true || base.tool_call === true ? ["tools"] : []), + ...(model.supports_output_json_schema === true || base.structured_output === true + ? ["structured_outputs"] + : []), + ], + // Requesty translates a single `reasoning_effort` into each vendor's native + // reasoning control: https://docs.requesty.ai/features/reasoning + reasoning: reasoning ? { mandatory: false, supported_efforts: [...REASONING_EFFORTS] } : undefined, + }; +} + +/** Context-length pricing bands. The first band is the flat `cost` of the model. */ +function pricingTiers(model: RequestyModel): NonNullable["tiers"] { + const tiers = (model.pricing ?? []) + .slice(1) + .map((band) => ({ + tier: { type: "context" as const, size: band.prompt_tokens_threshold }, + input: pricePerMillion(band.input_price ?? model.input_price), + output: pricePerMillion(band.output_price ?? model.output_price), + cache_read: chargedPricePerMillion(band.cached_price), + cache_write: chargedPricePerMillion(band.caching_price), + })); + return tiers.length > 0 ? tiers : undefined; +} + +/** Requesty prices are USD per token; zero means the route does not charge for it. */ +function chargedPerTokenPrice(price: number | undefined): string | undefined { + return price === undefined || price <= 0 ? undefined : String(price); +} + +function chargedPricePerMillion(price: number | undefined): number | undefined { + return price === undefined || price <= 0 ? undefined : pricePerMillion(price); +} + +function pricePerMillion(price: number): number { + return Math.round(price * TOKENS_PER_MILLION * PRICE_DECIMALS) / PRICE_DECIMALS; +} + +const metadataBySlug = new Map(); +const metadataByID = new Map(); + +/** `vertex/claude-opus-4@us-east5` and `anthropic/claude-opus-4` are the same model. */ +export function resolveRequestyBaseModel(modelID: string): string | undefined { + if (metadataBySlug.size === 0) indexMetadata(); + const slug = modelID.split("/").at(-1)?.split(/[@:]/)[0]; + return slug === undefined ? undefined : metadataBySlug.get(slug.toLowerCase()); +} + +function indexMetadata() { + for (const provider of readdirSync(MODELS_DIR)) { + for (const file of readdirSync(path.join(MODELS_DIR, provider))) { + if (!file.endsWith(".toml")) continue; + const modelID = file.slice(0, -".toml".length); + const slug = modelID.toLowerCase(); + // An ambiguous slug cannot be attributed to one lab from the route alone. + metadataBySlug.set(slug, metadataBySlug.has(slug) ? undefined : `${provider}/${modelID}`); + } + } +} + +function baseMetadata(modelID: string): BaseMetadata { + let metadata = metadataByID.get(modelID); + if (metadata === undefined) { + const file = readFileSync(path.join(MODELS_DIR, `${modelID}.toml`), "utf8"); + metadata = BaseMetadata.parse(Bun.TOML.parse(file)); + metadataByID.set(modelID, metadata); + } + return metadata; +} diff --git a/packages/core/test/sync.test.ts b/packages/core/test/sync.test.ts index 7a62dd64947..84281386dfb 100644 --- a/packages/core/test/sync.test.ts +++ b/packages/core/test/sync.test.ts @@ -35,6 +35,11 @@ import { import { buildLLMGatewayModel, type LLMGatewayModel } from "../src/sync/providers/llmgateway.js"; import { openai, parseOpenAIModels } from "../src/sync/providers/openai.js"; import { pioneer } from "../src/sync/providers/pioneer.js"; +import { + buildRequestyModel, + resolveRequestyBaseModel, + type RequestyModel, +} from "../src/sync/providers/requesty.js"; import { google, shouldTrackGoogleModel } from "../src/sync/providers/google.js"; import { resolveVeniceBaseModel } from "../src/sync/providers/venice.js"; import { buildVercelModel, vercel } from "../src/sync/providers/vercel.js"; @@ -1535,6 +1540,90 @@ test("maps EmpirioLabs aliases to canonical model metadata", () => { expect(resolveEmpiriolabsBaseModel("step-3-5-flash")).toBe("stepfun/step-3.5-flash"); }); +test("factors Requesty routes against canonical metadata", () => { + expect(buildRequestyModel(requestyModel(), "anthropic/claude-sonnet-5", undefined)).toEqual({ + base_model: "anthropic/claude-sonnet-5", + base_model_omit: undefined, + reasoning_options: [{ type: "effort", values: ["none", "low", "medium", "high", "max"] }], + structured_output: true, + cost: { input: 3, output: 15, cache_read: 0.3, cache_write: 3.75 }, + }); +}); + +test("keeps Requesty capabilities the catalog under-reports", () => { + expect(buildRequestyModel( + requestyModel({ + id: "xai/grok-4.5", + supports_reasoning: false, + supports_vision: false, + max_output_tokens: 0, + cached_price: 0, + caching_price: 0, + }), + "xai/grok-4.5", + undefined, + )).toEqual({ + base_model: "xai/grok-4.5", + base_model_omit: undefined, + reasoning_options: [{ type: "effort", values: ["none", "low", "medium", "high", "max"] }], + limit: { context: 1_000_000 }, + cost: { input: 3, output: 15 }, + }); +}); + +test("maps Requesty context pricing bands to cost tiers", () => { + expect(buildRequestyModel( + requestyModel({ + pricing: [ + { prompt_tokens_threshold: 0, input_price: 0.000003, output_price: 0.000015 }, + { + prompt_tokens_threshold: 200_000, + input_price: 0.000006, + output_price: 0.0000225, + cached_price: 0.0000006, + caching_price: 0.0000075, + }, + ], + }), + "anthropic/claude-sonnet-5", + undefined, + ).cost?.tiers).toEqual([ + { + tier: { type: "context", size: 200_000 }, + input: 6, + output: 22.5, + cache_read: 0.6, + cache_write: 7.5, + }, + ]); +}); + +test("resolves Requesty hosting, region, and service-tier routes to metadata", () => { + expect(resolveRequestyBaseModel("zai/glm-5.2")).toBe("zhipuai/glm-5.2"); + expect(resolveRequestyBaseModel("moonshot/kimi-k3")).toBe("moonshotai/kimi-k3"); + expect(resolveRequestyBaseModel("openai/gpt-5.4:flex")).toBe("openai/gpt-5.4"); + expect(resolveRequestyBaseModel("vertex/claude-sonnet-5@us-east5")).toBe("anthropic/claude-sonnet-5"); + expect(resolveRequestyBaseModel("novita/qwen/qwen3-235b-a22b-fp8")).toBeUndefined(); +}); + +function requestyModel(overrides: Partial = {}): RequestyModel { + return { + id: "anthropic/claude-sonnet-5", + created: 1_782_777_600, + context_window: 1_000_000, + max_output_tokens: 128_000, + input_price: 0.000003, + output_price: 0.000015, + cached_price: 0.0000003, + caching_price: 0.00000375, + supports_vision: true, + supports_reasoning: true, + supports_tool_calling: true, + supports_output_json_schema: true, + ...overrides, + }; +} + function unavailableStub(): OpenRouterModel { return openRouterModel({ id: "~anthropic/claude-fable-latest", diff --git a/sync.md b/sync.md index 9322ba50ba2..9f9a39caa10 100644 --- a/sync.md +++ b/sync.md @@ -253,6 +253,20 @@ Venice is implemented in `packages/core/src/sync/providers/venice.ts`. - Every Venice model uses `base_model`; flattened IDs are matched to provider-agnostic metadata before provider-specific overrides are written. - Every Venice model declares `reasoning_options`; models without API-provided effort levels use an empty array. +## Requesty Notes + +Requesty is implemented in `packages/core/src/sync/providers/requesty.ts`. + +- Run it with `bun models:sync requesty` or `bun requesty:sync`. +- Source endpoint: `https://router.requesty.ai/v1/models`; no auth required and no key is sent, so the run only sees catalog routes. +- Requesty routes are gateway data (price, limits, capability flags) on top of a model the catalog already describes, so each route is shaped into OpenRouter's model shape and built with `buildOpenRouterModel`. Everything else — modalities, factoring, description, `reasoning_options` — comes from the shared builder. +- Route IDs map directly to TOML paths under `providers/requesty/models`, so `vertex/claude-opus-4-5@us-east5` lives in `providers/requesty/models/vertex/claude-opus-4-5@us-east5.toml`. Every route Requesty serves gets a file, including hosting prefixes (`vertex/`, `bedrock/`, `azure/`, …), regions (`@us-east5`) and service tiers (`:flex`): those are the IDs callers pass to the gateway. +- Base metadata is resolved by model slug, not by route prefix, with the region/tier suffix stripped: `vertex/claude-opus-4-5@us-east5` and `anthropic/claude-opus-4-5` both inherit `models/anthropic/claude-opus-4-5.toml`. A slug shared by two labs is treated as unresolvable. +- Routes without a `models/` entry keep any authored file untouched and are reported in the sync notice; adding the metadata entry is enough to bring them in on the next run. +- API prices are USD per token, matching OpenRouter's unit, so they pass through the shared price conversion to per-1M numbers. Zero cache prices mean "not charged" and are dropped. `pricing` bands (context-length overrides) become `cost.tiers`; the flat prices stay the base band. +- Capability flags may only raise a capability, never clear one that the base metadata asserts: the flags describe the controls the gateway exposes, and always-on reasoning models (`xai/grok-4`, `deepseek/deepseek-reasoner`) report `supports_reasoning: false` while some multimodal routes report `supports_vision: false`. +- Reasoning models get a single `effort` option: Requesty accepts one `reasoning_effort` for every vendor and translates it into that vendor's native control (). + ## Standalone Generators Some provider scripts in `packages/core/script/generate-*.ts` are not wired into `bun models:sync`. When updating those scripts, preserve existing `base_model` and `base_model_omit` fields for generated TOMLs that already use model metadata inheritance. New inheritance-aware output should use `base_model`; do not reintroduce legacy `[extends]` syntax. From d2187b47f357cde571e6b819d7cc929bdce4a011 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 28 Jul 2026 18:18:47 +0000 Subject: [PATCH 2/2] chore(sync): sync the Requesty model catalog Co-Authored-By: john --- .../requesty/models/alibaba/qwen-max.toml | 8 ++++ .../requesty/models/alibaba/qwen-plus.toml | 15 +++++++ .../requesty/models/alibaba/qwen-turbo.toml | 12 ++++++ .../models/alibaba/qwen3-coder-flash.toml | 11 +++++ .../models/alibaba/qwen3-coder-plus.toml | 6 +++ .../requesty/models/alibaba/qwen3-max.toml | 6 +++ .../requesty/models/alibaba/qwen3.6-plus.toml | 12 ++++++ .../requesty/models/alibaba/qwen3.7-max.toml | 15 +++++++ .../requesty/models/alibaba/qwen3.7-plus.toml | 16 ++++++++ .../models/anthropic/claude-3-7-sonnet.toml | 26 ------------ .../models/anthropic/claude-fable-5.toml | 12 ++++++ .../models/anthropic/claude-haiku-4-5.toml | 29 ++++---------- .../models/anthropic/claude-opus-4-1.toml | 5 ++- .../models/anthropic/claude-opus-4-5.toml | 29 ++++---------- .../models/anthropic/claude-opus-4-6.toml | 40 ++++++------------- .../models/anthropic/claude-opus-4-7.toml | 12 ++++++ .../models/anthropic/claude-opus-4-8.toml | 12 ++++++ .../models/anthropic/claude-opus-4.toml | 26 ------------ .../models/anthropic/claude-opus-5.toml | 12 ++++++ .../models/anthropic/claude-sonnet-4-5.toml | 5 ++- .../models/anthropic/claude-sonnet-4-6.toml | 40 ++++++------------- .../models/anthropic/claude-sonnet-4.toml | 9 ----- .../models/anthropic/claude-sonnet-5.toml | 12 ++++++ .../models/azure/gpt-4.1-mini@eastus2.toml | 6 +++ .../azure/gpt-4.1-mini@francecentral.toml | 6 +++ .../models/azure/gpt-4.1-mini@uksouth.toml | 6 +++ .../models/azure/gpt-4.1-mini@westus3.toml | 6 +++ .../requesty/models/azure/gpt-4.1-nano.toml | 6 +++ .../models/azure/gpt-4.1-nano@eastus2.toml | 11 +++++ .../azure/gpt-4.1-nano@francecentral.toml | 11 +++++ .../azure/gpt-4.1-nano@swedencentral.toml | 11 +++++ .../models/azure/gpt-4.1-nano@uksouth.toml | 11 +++++ .../models/azure/gpt-4.1-nano@westus3.toml | 11 +++++ providers/requesty/models/azure/gpt-4.1.toml | 6 +++ .../models/azure/gpt-4.1@eastus2.toml | 6 +++ .../models/azure/gpt-4.1@francecentral.toml | 6 +++ .../models/azure/gpt-4.1@swedencentral.toml | 6 +++ .../models/azure/gpt-4.1@uksouth.toml | 6 +++ .../models/azure/gpt-4.1@westus3.toml | 6 +++ .../models/azure/gpt-4o-mini@eastus2.toml | 9 +++++ .../azure/gpt-4o-mini@swedencentral.toml | 9 +++++ .../requesty/models/azure/gpt-5-mini.toml | 15 +++++++ .../models/azure/gpt-5-mini@eastus2.toml | 15 +++++++ .../azure/gpt-5-mini@francecentral.toml | 15 +++++++ .../azure/gpt-5-mini@swedencentral.toml | 15 +++++++ .../models/azure/gpt-5-mini@uksouth.toml | 15 +++++++ .../requesty/models/azure/gpt-5-nano.toml | 15 +++++++ .../models/azure/gpt-5-nano@eastus2.toml | 15 +++++++ .../azure/gpt-5-nano@francecentral.toml | 15 +++++++ .../azure/gpt-5-nano@swedencentral.toml | 15 +++++++ providers/requesty/models/azure/gpt-5.1.toml | 15 +++++++ .../models/azure/gpt-5.1@eastus2.toml | 15 +++++++ .../models/azure/gpt-5.1@francecentral.toml | 15 +++++++ .../models/azure/gpt-5.1@swedencentral.toml | 15 +++++++ .../models/azure/gpt-5.2-codex@eastus2.toml | 10 +++++ .../models/azure/gpt-5.2@eastus2.toml | 15 +++++++ .../models/azure/gpt-5.3-codex@eastus2.toml | 10 +++++ .../requesty/models/azure/gpt-5.4-mini.toml | 10 +++++ .../models/azure/gpt-5.4-mini@eastus2.toml | 10 +++++ providers/requesty/models/azure/gpt-5.4.toml | 10 +++++ .../models/azure/gpt-5.4@eastus2.toml | 10 +++++ .../models/azure/gpt-5.4@francecentral.toml | 10 +++++ .../models/azure/gpt-5.4@swedencentral.toml | 10 +++++ .../models/azure/gpt-5.5@eastus2.toml | 10 +++++ .../models/azure/gpt-5.5@swedencentral.toml | 10 +++++ .../models/azure/gpt-5.6-luna@eastus2.toml | 10 +++++ .../azure/gpt-5.6-luna@swedencentral.toml | 10 +++++ .../models/azure/gpt-5.6-sol@eastus2.toml | 10 +++++ .../azure/gpt-5.6-sol@swedencentral.toml | 10 +++++ .../models/azure/gpt-5.6-terra@eastus2.toml | 10 +++++ .../azure/gpt-5.6-terra@swedencentral.toml | 10 +++++ providers/requesty/models/azure/gpt-5.toml | 15 +++++++ .../requesty/models/azure/gpt-5@eastus2.toml | 15 +++++++ .../models/azure/gpt-5@francecentral.toml | 15 +++++++ .../models/azure/gpt-5@swedencentral.toml | 15 +++++++ .../requesty/models/azure/gpt-5@uksouth.toml | 15 +++++++ .../models/azure/o4-mini@eastus2.toml | 10 +++++ .../models/azure/o4-mini@francecentral.toml | 10 +++++ .../models/azure/o4-mini@swedencentral.toml | 10 +++++ .../models/azure/o4-mini@westus3.toml | 10 +++++ .../gpt-4.1-mini@eastus2.toml | 6 +++ .../gpt-4.1-mini@francecentral.toml | 6 +++ .../gpt-4.1-mini@westus3.toml | 6 +++ .../azure/openai-responses/gpt-4.1-nano.toml | 6 +++ .../gpt-4.1-nano@eastus2.toml | 6 +++ .../gpt-4.1-nano@francecentral.toml | 6 +++ .../gpt-4.1-nano@swedencentral.toml | 6 +++ .../gpt-4.1-nano@westus3.toml | 6 +++ .../azure/openai-responses/gpt-4.1.toml | 6 +++ .../openai-responses/gpt-4.1@eastus2.toml | 6 +++ .../gpt-4.1@francecentral.toml | 6 +++ .../gpt-4.1@swedencentral.toml | 6 +++ .../openai-responses/gpt-4.1@westus3.toml | 6 +++ .../openai-responses/gpt-5.4-pro@eastus2.toml | 11 +++++ .../openai-responses/gpt-5.4@eastus2.toml | 10 +++++ .../gpt-5.4@francecentral.toml | 10 +++++ .../gpt-5.4@swedencentral.toml | 10 +++++ .../openai-responses/gpt-5.5@eastus2.toml | 10 +++++ .../gpt-5.5@swedencentral.toml | 10 +++++ .../gpt-5.6-luna@eastus2.toml | 10 +++++ .../gpt-5.6-luna@swedencentral.toml | 10 +++++ .../openai-responses/gpt-5.6-sol@eastus2.toml | 10 +++++ .../gpt-5.6-sol@swedencentral.toml | 10 +++++ .../gpt-5.6-terra@eastus2.toml | 10 +++++ .../gpt-5.6-terra@swedencentral.toml | 10 +++++ .../bedrock/claude-fable-5@us-east-1.toml | 12 ++++++ .../models/bedrock/claude-haiku-4-5.toml | 12 ++++++ .../claude-haiku-4-5@ap-northeast-1.toml | 12 ++++++ .../claude-haiku-4-5@eu-central-1.toml | 12 ++++++ .../bedrock/claude-haiku-4-5@eu-north-1.toml | 12 ++++++ .../bedrock/claude-haiku-4-5@eu-west-1.toml | 12 ++++++ .../bedrock/claude-haiku-4-5@eu-west-3.toml | 12 ++++++ .../bedrock/claude-haiku-4-5@us-east-1.toml | 12 ++++++ .../bedrock/claude-haiku-4-5@us-east-2.toml | 12 ++++++ .../bedrock/claude-haiku-4-5@us-west-2.toml | 12 ++++++ .../models/bedrock/claude-opus-4-5.toml | 12 ++++++ .../bedrock/claude-opus-4-5@eu-central-1.toml | 12 ++++++ .../bedrock/claude-opus-4-5@eu-north-1.toml | 12 ++++++ .../bedrock/claude-opus-4-5@eu-west-1.toml | 12 ++++++ .../bedrock/claude-opus-4-5@eu-west-3.toml | 12 ++++++ .../bedrock/claude-opus-4-5@us-east-1.toml | 12 ++++++ .../bedrock/claude-opus-4-5@us-east-2.toml | 12 ++++++ .../bedrock/claude-opus-4-5@us-west-2.toml | 12 ++++++ .../models/bedrock/claude-opus-4-6.toml | 12 ++++++ .../models/bedrock/claude-opus-4-7.toml | 12 ++++++ .../bedrock/claude-opus-4-7@eu-central-1.toml | 12 ++++++ .../bedrock/claude-opus-4-7@eu-north-1.toml | 12 ++++++ .../bedrock/claude-opus-4-7@eu-west-1.toml | 12 ++++++ .../bedrock/claude-opus-4-7@eu-west-3.toml | 12 ++++++ .../models/bedrock/claude-opus-4-8.toml | 12 ++++++ .../claude-opus-4-8@ap-northeast-1.toml | 12 ++++++ .../bedrock/claude-opus-4-8@eu-central-1.toml | 12 ++++++ .../bedrock/claude-opus-4-8@eu-north-1.toml | 12 ++++++ .../bedrock/claude-opus-4-8@eu-west-1.toml | 12 ++++++ .../bedrock/claude-opus-4-8@eu-west-3.toml | 12 ++++++ .../models/bedrock/claude-opus-5.toml | 12 ++++++ .../bedrock/claude-opus-5@ap-northeast-1.toml | 12 ++++++ .../bedrock/claude-opus-5@eu-central-1.toml | 12 ++++++ .../bedrock/claude-opus-5@eu-north-1.toml | 12 ++++++ .../bedrock/claude-opus-5@eu-west-1.toml | 12 ++++++ .../bedrock/claude-opus-5@eu-west-3.toml | 12 ++++++ .../models/bedrock/claude-sonnet-4-5.toml | 12 ++++++ .../claude-sonnet-4-5@eu-central-1.toml | 12 ++++++ .../bedrock/claude-sonnet-4-5@eu-north-1.toml | 12 ++++++ .../bedrock/claude-sonnet-4-5@eu-west-1.toml | 12 ++++++ .../bedrock/claude-sonnet-4-5@eu-west-3.toml | 12 ++++++ .../bedrock/claude-sonnet-4-5@us-east-1.toml | 12 ++++++ .../bedrock/claude-sonnet-4-5@us-east-2.toml | 12 ++++++ .../bedrock/claude-sonnet-4-5@us-west-2.toml | 12 ++++++ .../models/bedrock/claude-sonnet-4-6.toml | 12 ++++++ .../claude-sonnet-4-6@ap-northeast-1.toml | 12 ++++++ .../claude-sonnet-4-6@eu-central-1.toml | 12 ++++++ .../bedrock/claude-sonnet-4-6@eu-north-1.toml | 12 ++++++ .../bedrock/claude-sonnet-4-6@eu-west-1.toml | 12 ++++++ .../bedrock/claude-sonnet-4-6@eu-west-3.toml | 12 ++++++ .../bedrock/claude-sonnet-4-6@us-east-1.toml | 12 ++++++ .../bedrock/claude-sonnet-4-6@us-east-2.toml | 12 ++++++ .../bedrock/claude-sonnet-4-6@us-west-2.toml | 12 ++++++ .../models/bedrock/claude-sonnet-5.toml | 12 ++++++ .../claude-sonnet-5@ap-southeast-2.toml | 12 ++++++ .../bedrock/claude-sonnet-5@eu-central-1.toml | 12 ++++++ .../bedrock/claude-sonnet-5@eu-north-1.toml | 12 ++++++ .../bedrock/claude-sonnet-5@eu-west-1.toml | 12 ++++++ .../bedrock/claude-sonnet-5@eu-west-2.toml | 12 ++++++ .../bedrock/claude-sonnet-5@us-east-1.toml | 12 ++++++ .../bedrock/claude-sonnet-5@us-east-2.toml | 12 ++++++ .../bedrock/claude-sonnet-5@us-west-2.toml | 12 ++++++ .../models/bedrock/gpt-5.4@us-east-1.toml | 10 +++++ .../models/bedrock/gpt-5.4@us-east-2.toml | 10 +++++ .../models/bedrock/gpt-5.4@us-west-2.toml | 10 +++++ .../models/bedrock/gpt-5.5@us-east-1.toml | 10 +++++ .../models/bedrock/gpt-5.5@us-east-2.toml | 10 +++++ .../models/bedrock/kimi-k2.5@eu-north-1.toml | 15 +++++++ .../models/bedrock/kimi-k2.5@eu-west-2.toml | 15 +++++++ .../models/bedrock/kimi-k2.5@us-east-1.toml | 13 ++++++ .../models/bedrock/kimi-k2.5@us-east-2.toml | 13 ++++++ .../models/bedrock/kimi-k2.5@us-west-2.toml | 13 ++++++ .../bedrock/minimax-m2.5@eu-central-1.toml | 14 +++++++ .../bedrock/minimax-m2.5@eu-north-1.toml | 14 +++++++ .../bedrock/minimax-m2.5@eu-south-1.toml | 14 +++++++ .../bedrock/minimax-m2.5@eu-west-1.toml | 14 +++++++ .../bedrock/minimax-m2.5@us-east-1.toml | 14 +++++++ .../bedrock/minimax-m2.5@us-east-2.toml | 14 +++++++ .../bedrock/minimax-m2.5@us-west-2.toml | 14 +++++++ .../models/coding/gemini-2.5-flash.toml | 14 +++++++ .../gemini-2.5-flash@europe-central2.toml | 14 +++++++ .../gemini-2.5-flash@europe-north1.toml | 14 +++++++ .../coding/gemini-2.5-flash@europe-west1.toml | 14 +++++++ .../coding/gemini-2.5-flash@europe-west4.toml | 14 +++++++ .../coding/gemini-2.5-flash@europe-west8.toml | 14 +++++++ .../coding/gemini-2.5-flash@us-central1.toml | 14 +++++++ .../coding/gemini-2.5-flash@us-east1.toml | 14 +++++++ .../coding/gemini-2.5-flash@us-east5.toml | 14 +++++++ .../coding/gemini-2.5-flash@us-south1.toml | 14 +++++++ .../coding/gemini-2.5-flash@us-west1.toml | 14 +++++++ .../models/coding/gemini-2.5-pro.toml | 14 +++++++ .../gemini-2.5-pro@europe-central2.toml | 14 +++++++ .../coding/gemini-2.5-pro@europe-north1.toml | 14 +++++++ .../coding/gemini-2.5-pro@europe-west1.toml | 14 +++++++ .../coding/gemini-2.5-pro@europe-west4.toml | 14 +++++++ .../coding/gemini-2.5-pro@europe-west8.toml | 14 +++++++ .../coding/gemini-2.5-pro@us-central1.toml | 14 +++++++ .../coding/gemini-2.5-pro@us-east1.toml | 14 +++++++ .../coding/gemini-2.5-pro@us-east5.toml | 14 +++++++ .../coding/gemini-2.5-pro@us-south1.toml | 14 +++++++ .../coding/gemini-2.5-pro@us-west1.toml | 14 +++++++ .../deepinfra/Qwen/Qwen3-235B-A22B.toml | 15 +++++++ .../models/deepinfra/Qwen/Qwen3-32B.toml | 14 +++++++ .../Qwen/Qwen3-Coder-480B-A35B-Instruct.toml | 7 ++++ .../models/deepinfra/Qwen/Qwen3-Max.toml | 10 +++++ .../models/deepinfra/Qwen/Qwen3.5-27B.toml | 9 +++++ .../deepinfra/Qwen/Qwen3.5-35B-A3B.toml | 10 +++++ .../deepinfra/Qwen/Qwen3.5-397B-A17B.toml | 10 +++++ .../deepinfra/XiaomiMiMo/MiMo-V2.5-Pro.toml | 11 +++++ .../deepinfra/XiaomiMiMo/MiMo-V2.5.toml | 14 +++++++ .../deepinfra/deepseek-ai/DeepSeek-R1.toml | 15 +++++++ .../deepseek-ai/DeepSeek-V4-Flash.toml | 13 ++++++ .../deepseek-ai/DeepSeek-V4-Pro.toml | 13 ++++++ .../deepinfra/google/gemma-4-26B-A4B-it.toml | 10 +++++ .../deepinfra/google/gemma-4-31B-it.toml | 9 +++++ .../meta-llama/Llama-3.3-70B-Instruct.toml | 11 +++++ .../deepinfra/moonshotai/Kimi-K2.6.toml | 10 +++++ .../nvidia/Nemotron-3-Nano-30B-A3B.toml | 10 +++++ .../models/deepinfra/zai-org/GLM-4.5-Air.toml | 14 +++++++ .../models/deepinfra/zai-org/GLM-4.5.toml | 14 +++++++ .../models/deepinfra/zai-org/GLM-5.1.toml | 13 ++++++ .../models/deepseek/deepseek-chat.toml | 8 ++++ .../models/deepseek/deepseek-reasoner.toml | 12 ++++++ .../models/deepseek/deepseek-v4-flash.toml | 10 +++++ .../models/deepseek/deepseek-v4-pro.toml | 10 +++++ .../models/doubleword/deepseek-v4-flash.toml | 13 ++++++ .../doubleword/deepseek-v4-flash:flex.toml | 13 ++++++ .../models/doubleword/deepseek-v4-pro.toml | 13 ++++++ .../doubleword/deepseek-v4-pro:flex.toml | 13 ++++++ .../requesty/models/doubleword/glm-5.2.toml | 12 ++++++ .../models/doubleword/glm-5.2:flex.toml | 12 ++++++ .../models/fireworks/deepseek-v4-flash.toml | 13 ++++++ .../models/fireworks/deepseek-v4-pro.toml | 13 ++++++ .../requesty/models/fireworks/glm-5.1.toml | 14 +++++++ .../requesty/models/fireworks/glm-5.2.toml | 10 +++++ .../models/fireworks/gpt-oss-120b.toml | 13 ++++++ .../models/fireworks/gpt-oss-20b.toml | 13 ++++++ .../requesty/models/fireworks/kimi-k2.6.toml | 13 ++++++ .../models/fireworks/kimi-k2.7-code.toml | 10 +++++ .../requesty/models/fireworks/kimi-k3.toml | 13 ++++++ .../models/fireworks/minimax-m2.7.toml | 15 +++++++ .../requesty/models/fireworks/minimax-m3.toml | 14 +++++++ .../models/fireworks/qwen3.7-plus.toml | 15 +++++++ .../models/google/gemini-2.5-flash-lite.toml | 13 ++++++ .../models/google/gemini-2.5-flash.toml | 28 ++++--------- .../models/google/gemini-2.5-pro.toml | 7 +++- .../models/google/gemini-3-flash-preview.toml | 23 +++-------- .../models/google/gemini-3-pro-preview.toml | 29 +++++--------- .../models/google/gemini-3.1-flash-image.toml | 11 +++++ .../models/google/gemini-3.1-flash-lite.toml | 13 ++++++ .../models/google/gemini-3.1-pro-preview.toml | 14 +++++++ .../models/google/gemma-4-31b-it.toml | 12 ++++++ .../models/groq/openai/gpt-oss-120b.toml | 10 +++++ .../models/groq/openai/gpt-oss-20b.toml | 10 +++++ .../requesty/models/inceptron/glm-5.2.toml | 13 ++++++ .../requesty/models/inceptron/kimi-k2.6.toml | 10 +++++ .../models/inceptron/kimi-k2.7-Code.toml | 14 +++++++ .../models/inceptron/minimax-m2.5.toml | 15 +++++++ .../minimaxi/minimax-m2.5-highspeed.toml | 16 ++++++++ .../models/minimaxi/minimax-m2.5.toml | 16 ++++++++ .../minimaxi/minimax-m2.7-highspeed.toml | 16 ++++++++ .../models/minimaxi/minimax-m2.7.toml | 16 ++++++++ .../requesty/models/minimaxi/minimax-m2.toml | 15 +++++++ .../requesty/models/minimaxi/minimax-m3.toml | 14 +++++++ .../models/mistral/codestral-latest.toml | 10 +++++ .../models/mistral/mistral-large-latest.toml | 10 +++++ .../models/mistral/mistral-medium-latest.toml | 13 ++++++ .../models/mistral/mistral-small-2603.toml | 11 +++++ .../models/mistral/mistral-small-latest.toml | 11 +++++ .../requesty/models/moonshot/kimi-k2.5.toml | 10 +++++ .../requesty/models/moonshot/kimi-k2.6.toml | 10 +++++ .../models/moonshot/kimi-k2.7-code.toml | 10 +++++ .../requesty/models/moonshot/kimi-k3.toml | 14 +++++++ .../nebius/deepseek-ai/deepseek-v4-pro.toml | 14 +++++++ providers/requesty/models/nebius/glm-5.2.toml | 9 +++++ providers/requesty/models/nebius/kimi-k3.toml | 9 +++++ .../meta-llama/Llama-3.3-70B-Instruct.toml | 8 ++++ .../models/nebius/minimaxi/minimax-m2.5.toml | 14 +++++++ .../models/nebius/moonshotai/kimi-k2.6.toml | 14 +++++++ .../nvidia/nemotron-3-super-120b-a12b.toml | 14 +++++++ .../nvidia/nemotron-3-ultra-550b-a55b.toml | 14 +++++++ .../models/nebius/openai/gpt-oss-120b.toml | 14 +++++++ .../models/nebius/qwen/qwen3-32b.toml | 14 +++++++ .../qwen/qwen3-next-80b-a3b-thinking.toml | 14 +++++++ .../models/nebius/qwen/qwen3.5-397b-a17b.toml | 13 ++++++ .../models/nebius/zai-org/glm-5.1.toml | 10 +++++ providers/requesty/models/novita/GLM-5.toml | 14 +++++++ .../models/novita/deepseek/deepseek-r1.toml | 14 +++++++ .../novita/deepseek/deepseek-v4-flash.toml | 12 ++++++ .../novita/google/gemma-4-26b-a4b-it.toml | 13 ++++++ .../meta-llama/llama-3.3-70b-instruct.toml | 11 +++++ .../minimax/minimax-m2.7-highspeed.toml | 10 +++++ .../models/novita/minimax/minimax-m2.7.toml | 15 +++++++ .../models/novita/mistralai/mistral-nemo.toml | 10 +++++ .../models/novita/qwen/qwen3.5-397b-a17b.toml | 10 +++++ .../models/novita/stepfun/step-3.7-flash.toml | 15 +++++++ .../requesty/models/novita/tencent/hy3.toml | 15 +++++++ .../models/novita/zai-org/glm-4.6.toml | 11 +++++ .../models/novita/zai-org/glm-5.1.toml | 12 ++++++ .../nvidia/nemotron-3-nano-30b-a3b.toml | 10 +++++ ...emotron-3-nano-omni-30b-a3b-reasoning.toml | 14 +++++++ .../nvidia/nemotron-3-super-120b-a12b.toml | 14 +++++++ .../nvidia/nemotron-3-ultra-550b-a55b.toml | 14 +++++++ .../nvidia/nemotron-3.5-content-safety.toml | 13 ++++++ .../models/openai-responses/gpt-4.1-mini.toml | 6 +++ .../models/openai-responses/gpt-4.1-nano.toml | 6 +++ .../models/openai-responses/gpt-4.1.toml | 6 +++ .../models/openai-responses/gpt-5-codex.toml | 11 +++++ .../models/openai-responses/gpt-5-mini.toml | 10 +++++ .../models/openai-responses/gpt-5-nano.toml | 10 +++++ .../models/openai-responses/gpt-5-pro.toml | 10 +++++ .../openai-responses/gpt-5.1-codex.toml | 10 +++++ .../models/openai-responses/gpt-5.1.toml | 10 +++++ .../openai-responses/gpt-5.2-codex.toml | 10 +++++ .../models/openai-responses/gpt-5.2.toml | 10 +++++ .../openai-responses/gpt-5.3-codex.toml | 10 +++++ .../models/openai-responses/gpt-5.4-mini.toml | 10 +++++ .../models/openai-responses/gpt-5.4-nano.toml | 10 +++++ .../models/openai-responses/gpt-5.4-pro.toml | 11 +++++ .../models/openai-responses/gpt-5.4.toml | 10 +++++ .../models/openai-responses/gpt-5.5-pro.toml | 9 +++++ .../models/openai-responses/gpt-5.5.toml | 10 +++++ .../models/openai-responses/gpt-5.6-luna.toml | 10 +++++ .../models/openai-responses/gpt-5.6-sol.toml | 10 +++++ .../openai-responses/gpt-5.6-terra.toml | 10 +++++ .../models/openai-responses/gpt-5.toml | 10 +++++ .../models/openai-responses/o3-mini.toml | 10 +++++ .../models/openai-responses/o3-pro.toml | 10 +++++ .../models/openai-responses/o4-mini.toml | 10 +++++ .../requesty/models/openai/gpt-4.1-mini.toml | 25 ++---------- .../requesty/models/openai/gpt-4.1-nano.toml | 6 +++ providers/requesty/models/openai/gpt-4.1.toml | 3 -- .../models/openai/gpt-4o-2024-05-13.toml | 6 +++ .../models/openai/gpt-4o-2024-08-06.toml | 6 +++ .../models/openai/gpt-4o-2024-11-20.toml | 6 +++ .../requesty/models/openai/gpt-4o-mini.toml | 23 ++--------- providers/requesty/models/openai/gpt-4o.toml | 6 +++ .../requesty/models/openai/gpt-5-chat.toml | 25 ------------ .../requesty/models/openai/gpt-5-codex.toml | 26 ------------ .../requesty/models/openai/gpt-5-image.toml | 26 ------------ .../requesty/models/openai/gpt-5-mini.toml | 28 ++++--------- .../models/openai/gpt-5-mini:flex.toml | 10 +++++ .../models/openai/gpt-5-mini:priority.toml | 10 +++++ .../requesty/models/openai/gpt-5-nano.toml | 28 ++++--------- .../models/openai/gpt-5-nano:flex.toml | 10 +++++ .../requesty/models/openai/gpt-5-pro.toml | 8 ---- .../models/openai/gpt-5.1-codex-max.toml | 26 ------------ .../models/openai/gpt-5.1-codex-mini.toml | 26 ------------ .../requesty/models/openai/gpt-5.1-codex.toml | 26 ------------ providers/requesty/models/openai/gpt-5.1.toml | 27 +++---------- .../requesty/models/openai/gpt-5.2-codex.toml | 26 ------------ .../requesty/models/openai/gpt-5.2-pro.toml | 25 ------------ providers/requesty/models/openai/gpt-5.2.toml | 4 +- .../requesty/models/openai/gpt-5.3-codex.toml | 26 ------------ .../requesty/models/openai/gpt-5.4-mini.toml | 10 +++++ .../requesty/models/openai/gpt-5.4-nano.toml | 10 +++++ .../requesty/models/openai/gpt-5.4-pro.toml | 27 ------------- providers/requesty/models/openai/gpt-5.4.toml | 4 +- providers/requesty/models/openai/gpt-5.5.toml | 10 +++++ .../requesty/models/openai/gpt-5.6-luna.toml | 10 +++++ .../requesty/models/openai/gpt-5.6-sol.toml | 10 +++++ .../requesty/models/openai/gpt-5.6-terra.toml | 10 +++++ providers/requesty/models/openai/gpt-5.toml | 28 ++++--------- .../requesty/models/openai/gpt-5:flex.toml | 10 +++++ .../models/openai/gpt-5:priority.toml | 10 +++++ providers/requesty/models/openai/o1.toml | 10 +++++ providers/requesty/models/openai/o1:high.toml | 10 +++++ providers/requesty/models/openai/o1:low.toml | 10 +++++ .../requesty/models/openai/o1:medium.toml | 10 +++++ providers/requesty/models/openai/o3-mini.toml | 10 +++++ .../requesty/models/openai/o3-mini:high.toml | 10 +++++ .../requesty/models/openai/o3-mini:low.toml | 10 +++++ .../models/openai/o3-mini:medium.toml | 10 +++++ providers/requesty/models/openai/o3.toml | 10 +++++ providers/requesty/models/openai/o3:flex.toml | 10 +++++ providers/requesty/models/openai/o4-mini.toml | 30 ++++---------- .../requesty/models/openai/o4-mini:flex.toml | 10 +++++ .../requesty/models/openai/o4-mini:high.toml | 10 +++++ .../requesty/models/openai/o4-mini:low.toml | 10 +++++ .../models/openai/o4-mini:medium.toml | 10 +++++ .../parasail/google/gemma-4-26B-A4B-it.toml | 10 +++++ .../models/parasail/kimi-k2.7-code.toml | 10 +++++ .../requesty/models/perplexity/sonar-pro.toml | 10 +++++ .../perplexity/sonar-reasoning-pro.toml | 15 +++++++ .../requesty/models/perplexity/sonar.toml | 11 +++++ .../requesty/models/poolside/laguna-m.1.toml | 12 ++++++ .../requesty/models/poolside/laguna-xs.2.toml | 12 ++++++ .../requesty/models/sakana/fugu-ultra.toml | 14 +++++++ .../models/sference/deepseek-v4-flash.toml | 14 +++++++ .../requesty/models/sference/glm-5.2.toml | 13 ++++++ .../requesty/models/sference/kimi-k3.toml | 13 ++++++ .../models/tensorx/deepseek-v4-flash.toml | 14 +++++++ .../models/tensorx/deepseek-v4-pro.toml | 14 +++++++ .../requesty/models/tensorx/glm-5.2.toml | 14 +++++++ .../models/tensorx/kimi-k2.7-code.toml | 10 +++++ .../requesty/models/tensorx/kimi-k3.toml | 13 ++++++ .../requesty/models/tensorx/minimax-m3.toml | 15 +++++++ .../models/thinkingmachines/inkling.toml | 15 +++++++ .../models/vertex/claude-fable-5.toml | 12 ++++++ .../models/vertex/claude-fable-5@eu.toml | 12 ++++++ .../models/vertex/claude-haiku-4-5.toml | 12 ++++++ .../vertex/claude-haiku-4-5@europe-west1.toml | 12 ++++++ .../vertex/claude-haiku-4-5@us-east5.toml | 12 ++++++ .../models/vertex/claude-opus-4-1.toml | 12 ++++++ .../vertex/claude-opus-4-1@us-east5.toml | 12 ++++++ .../models/vertex/claude-opus-4-5.toml | 12 ++++++ .../vertex/claude-opus-4-5@europe-west1.toml | 12 ++++++ .../vertex/claude-opus-4-5@us-east5.toml | 12 ++++++ .../models/vertex/claude-opus-4-6.toml | 12 ++++++ .../vertex/claude-opus-4-6@europe-west1.toml | 12 ++++++ .../vertex/claude-opus-4-6@us-east5.toml | 12 ++++++ .../models/vertex/claude-opus-4-7.toml | 12 ++++++ .../models/vertex/claude-opus-4-7@eu.toml | 12 ++++++ .../models/vertex/claude-opus-4-7@us.toml | 12 ++++++ .../models/vertex/claude-opus-4-8.toml | 12 ++++++ .../models/vertex/claude-opus-4-8@eu.toml | 12 ++++++ .../models/vertex/claude-opus-4-8@us.toml | 12 ++++++ .../requesty/models/vertex/claude-opus-5.toml | 12 ++++++ .../models/vertex/claude-opus-5@eu.toml | 12 ++++++ .../models/vertex/claude-opus-5@us.toml | 12 ++++++ .../models/vertex/claude-sonnet-4-5.toml | 12 ++++++ .../claude-sonnet-4-5@europe-west1.toml | 12 ++++++ .../vertex/claude-sonnet-4-5@us-east5.toml | 12 ++++++ .../models/vertex/claude-sonnet-4-6.toml | 15 +++++++ .../claude-sonnet-4-6@europe-west1.toml | 15 +++++++ .../vertex/claude-sonnet-4-6@us-east5.toml | 15 +++++++ .../models/vertex/claude-sonnet-5.toml | 12 ++++++ .../models/vertex/claude-sonnet-5@eu.toml | 12 ++++++ .../models/vertex/claude-sonnet-5@us.toml | 12 ++++++ .../models/vertex/gemini-2.5-flash-image.toml | 17 ++++++++ ...emini-2.5-flash-image@europe-central2.toml | 17 ++++++++ .../gemini-2.5-flash-image@europe-north1.toml | 17 ++++++++ ...ini-2.5-flash-image@europe-southwest1.toml | 17 ++++++++ .../gemini-2.5-flash-image@europe-west1.toml | 17 ++++++++ .../gemini-2.5-flash-image@europe-west4.toml | 17 ++++++++ .../gemini-2.5-flash-image@europe-west8.toml | 17 ++++++++ .../gemini-2.5-flash-image@us-central1.toml | 17 ++++++++ .../gemini-2.5-flash-image@us-east1.toml | 17 ++++++++ .../gemini-2.5-flash-image@us-east4.toml | 17 ++++++++ .../gemini-2.5-flash-image@us-east5.toml | 17 ++++++++ .../gemini-2.5-flash-image@us-south1.toml | 17 ++++++++ .../gemini-2.5-flash-image@us-west1.toml | 17 ++++++++ .../gemini-2.5-flash-image@us-west4.toml | 17 ++++++++ .../models/vertex/gemini-2.5-flash-lite.toml | 14 +++++++ ...gemini-2.5-flash-lite@europe-central2.toml | 14 +++++++ .../gemini-2.5-flash-lite@europe-north1.toml | 14 +++++++ .../gemini-2.5-flash-lite@europe-west1.toml | 14 +++++++ .../gemini-2.5-flash-lite@europe-west4.toml | 14 +++++++ .../gemini-2.5-flash-lite@europe-west8.toml | 14 +++++++ .../gemini-2.5-flash-lite@us-central1.toml | 14 +++++++ .../gemini-2.5-flash-lite@us-east1.toml | 14 +++++++ .../gemini-2.5-flash-lite@us-east5.toml | 14 +++++++ .../gemini-2.5-flash-lite@us-south1.toml | 14 +++++++ .../gemini-2.5-flash-lite@us-west1.toml | 14 +++++++ .../models/vertex/gemini-2.5-flash.toml | 14 +++++++ .../gemini-2.5-flash@europe-central2.toml | 14 +++++++ .../gemini-2.5-flash@europe-north1.toml | 14 +++++++ .../vertex/gemini-2.5-flash@europe-west1.toml | 14 +++++++ .../vertex/gemini-2.5-flash@europe-west4.toml | 14 +++++++ .../vertex/gemini-2.5-flash@europe-west8.toml | 14 +++++++ .../vertex/gemini-2.5-flash@us-central1.toml | 14 +++++++ .../vertex/gemini-2.5-flash@us-east1.toml | 14 +++++++ .../vertex/gemini-2.5-flash@us-east5.toml | 14 +++++++ .../vertex/gemini-2.5-flash@us-south1.toml | 14 +++++++ .../vertex/gemini-2.5-flash@us-west1.toml | 14 +++++++ .../models/vertex/gemini-2.5-pro.toml | 14 +++++++ .../gemini-2.5-pro@europe-central2.toml | 14 +++++++ .../vertex/gemini-2.5-pro@europe-north1.toml | 14 +++++++ .../vertex/gemini-2.5-pro@europe-west1.toml | 14 +++++++ .../vertex/gemini-2.5-pro@europe-west4.toml | 14 +++++++ .../vertex/gemini-2.5-pro@europe-west8.toml | 14 +++++++ .../vertex/gemini-2.5-pro@us-central1.toml | 14 +++++++ .../vertex/gemini-2.5-pro@us-east1.toml | 14 +++++++ .../vertex/gemini-2.5-pro@us-east5.toml | 14 +++++++ .../vertex/gemini-2.5-pro@us-south1.toml | 14 +++++++ .../vertex/gemini-2.5-pro@us-west1.toml | 14 +++++++ .../models/vertex/gemini-3-flash-preview.toml | 14 +++++++ .../vertex/gemini-3-flash-preview:flex.toml | 14 +++++++ .../models/vertex/gemini-3-pro-image.toml | 16 ++++++++ .../models/vertex/gemini-3-pro-preview.toml | 14 +++++++ .../models/vertex/gemini-3.1-flash-image.toml | 11 +++++ .../models/vertex/gemini-3.1-flash-lite.toml | 14 +++++++ .../vertex/gemini-3.1-flash-lite@eu.toml | 14 +++++++ .../vertex/gemini-3.1-flash-lite@us.toml | 14 +++++++ .../models/vertex/gemini-3.1-pro-preview.toml | 14 +++++++ .../vertex/gemini-3.1-pro-preview:flex.toml | 14 +++++++ .../models/vertex/gemini-3.5-flash-lite.toml | 13 ++++++ .../vertex/gemini-3.5-flash-lite@eu.toml | 13 ++++++ .../models/vertex/gemini-3.5-flash.toml | 14 +++++++ .../models/vertex/gemini-3.5-flash@eu.toml | 14 +++++++ .../models/vertex/gemini-3.5-flash@us.toml | 14 +++++++ .../models/vertex/gemini-3.6-flash.toml | 13 ++++++ .../requesty/models/xai/grok-4-fast.toml | 3 +- providers/requesty/models/xai/grok-4.3.toml | 11 +++++ providers/requesty/models/xai/grok-4.5.toml | 11 +++++ providers/requesty/models/xai/grok-4.toml | 9 +++-- .../requesty/models/xai/grok-build-0.1.toml | 10 +++++ .../requesty/models/xiaomi/mimo-v2.5-pro.toml | 11 +++++ .../requesty/models/xiaomi/mimo-v2.5.toml | 11 +++++ providers/requesty/models/zai/GLM-4.5.toml | 11 +++++ providers/requesty/models/zai/GLM-4.6.toml | 15 +++++++ providers/requesty/models/zai/GLM-4.7.toml | 15 +++++++ providers/requesty/models/zai/GLM-5.toml | 15 +++++++ providers/requesty/models/zai/glm-5.1.toml | 13 ++++++ providers/requesty/models/zai/glm-5.2.toml | 13 ++++++ 510 files changed, 5791 insertions(+), 641 deletions(-) create mode 100644 providers/requesty/models/alibaba/qwen-max.toml create mode 100644 providers/requesty/models/alibaba/qwen-plus.toml create mode 100644 providers/requesty/models/alibaba/qwen-turbo.toml create mode 100644 providers/requesty/models/alibaba/qwen3-coder-flash.toml create mode 100644 providers/requesty/models/alibaba/qwen3-coder-plus.toml create mode 100644 providers/requesty/models/alibaba/qwen3-max.toml create mode 100644 providers/requesty/models/alibaba/qwen3.6-plus.toml create mode 100644 providers/requesty/models/alibaba/qwen3.7-max.toml create mode 100644 providers/requesty/models/alibaba/qwen3.7-plus.toml delete mode 100644 providers/requesty/models/anthropic/claude-3-7-sonnet.toml create mode 100644 providers/requesty/models/anthropic/claude-fable-5.toml create mode 100644 providers/requesty/models/anthropic/claude-opus-4-7.toml create mode 100644 providers/requesty/models/anthropic/claude-opus-4-8.toml delete mode 100644 providers/requesty/models/anthropic/claude-opus-4.toml create mode 100644 providers/requesty/models/anthropic/claude-opus-5.toml delete mode 100644 providers/requesty/models/anthropic/claude-sonnet-4.toml create mode 100644 providers/requesty/models/anthropic/claude-sonnet-5.toml create mode 100644 providers/requesty/models/azure/gpt-4.1-mini@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-4.1-mini@francecentral.toml create mode 100644 providers/requesty/models/azure/gpt-4.1-mini@uksouth.toml create mode 100644 providers/requesty/models/azure/gpt-4.1-mini@westus3.toml create mode 100644 providers/requesty/models/azure/gpt-4.1-nano.toml create mode 100644 providers/requesty/models/azure/gpt-4.1-nano@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-4.1-nano@francecentral.toml create mode 100644 providers/requesty/models/azure/gpt-4.1-nano@swedencentral.toml create mode 100644 providers/requesty/models/azure/gpt-4.1-nano@uksouth.toml create mode 100644 providers/requesty/models/azure/gpt-4.1-nano@westus3.toml create mode 100644 providers/requesty/models/azure/gpt-4.1.toml create mode 100644 providers/requesty/models/azure/gpt-4.1@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-4.1@francecentral.toml create mode 100644 providers/requesty/models/azure/gpt-4.1@swedencentral.toml create mode 100644 providers/requesty/models/azure/gpt-4.1@uksouth.toml create mode 100644 providers/requesty/models/azure/gpt-4.1@westus3.toml create mode 100644 providers/requesty/models/azure/gpt-4o-mini@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-4o-mini@swedencentral.toml create mode 100644 providers/requesty/models/azure/gpt-5-mini.toml create mode 100644 providers/requesty/models/azure/gpt-5-mini@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-5-mini@francecentral.toml create mode 100644 providers/requesty/models/azure/gpt-5-mini@swedencentral.toml create mode 100644 providers/requesty/models/azure/gpt-5-mini@uksouth.toml create mode 100644 providers/requesty/models/azure/gpt-5-nano.toml create mode 100644 providers/requesty/models/azure/gpt-5-nano@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-5-nano@francecentral.toml create mode 100644 providers/requesty/models/azure/gpt-5-nano@swedencentral.toml create mode 100644 providers/requesty/models/azure/gpt-5.1.toml create mode 100644 providers/requesty/models/azure/gpt-5.1@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-5.1@francecentral.toml create mode 100644 providers/requesty/models/azure/gpt-5.1@swedencentral.toml create mode 100644 providers/requesty/models/azure/gpt-5.2-codex@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-5.2@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-5.3-codex@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-5.4-mini.toml create mode 100644 providers/requesty/models/azure/gpt-5.4-mini@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-5.4.toml create mode 100644 providers/requesty/models/azure/gpt-5.4@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-5.4@francecentral.toml create mode 100644 providers/requesty/models/azure/gpt-5.4@swedencentral.toml create mode 100644 providers/requesty/models/azure/gpt-5.5@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-5.5@swedencentral.toml create mode 100644 providers/requesty/models/azure/gpt-5.6-luna@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-5.6-luna@swedencentral.toml create mode 100644 providers/requesty/models/azure/gpt-5.6-sol@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-5.6-sol@swedencentral.toml create mode 100644 providers/requesty/models/azure/gpt-5.6-terra@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-5.6-terra@swedencentral.toml create mode 100644 providers/requesty/models/azure/gpt-5.toml create mode 100644 providers/requesty/models/azure/gpt-5@eastus2.toml create mode 100644 providers/requesty/models/azure/gpt-5@francecentral.toml create mode 100644 providers/requesty/models/azure/gpt-5@swedencentral.toml create mode 100644 providers/requesty/models/azure/gpt-5@uksouth.toml create mode 100644 providers/requesty/models/azure/o4-mini@eastus2.toml create mode 100644 providers/requesty/models/azure/o4-mini@francecentral.toml create mode 100644 providers/requesty/models/azure/o4-mini@swedencentral.toml create mode 100644 providers/requesty/models/azure/o4-mini@westus3.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-4.1-mini@eastus2.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-4.1-mini@francecentral.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-4.1-mini@westus3.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-4.1-nano.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-4.1-nano@eastus2.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-4.1-nano@francecentral.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-4.1-nano@swedencentral.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-4.1-nano@westus3.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-4.1.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-4.1@eastus2.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-4.1@francecentral.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-4.1@swedencentral.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-4.1@westus3.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-5.4-pro@eastus2.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-5.4@eastus2.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-5.4@francecentral.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-5.4@swedencentral.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-5.5@eastus2.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-5.5@swedencentral.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-5.6-luna@eastus2.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-5.6-luna@swedencentral.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-5.6-sol@eastus2.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-5.6-sol@swedencentral.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-5.6-terra@eastus2.toml create mode 100644 providers/requesty/models/azure/openai-responses/gpt-5.6-terra@swedencentral.toml create mode 100644 providers/requesty/models/bedrock/claude-fable-5@us-east-1.toml create mode 100644 providers/requesty/models/bedrock/claude-haiku-4-5.toml create mode 100644 providers/requesty/models/bedrock/claude-haiku-4-5@ap-northeast-1.toml create mode 100644 providers/requesty/models/bedrock/claude-haiku-4-5@eu-central-1.toml create mode 100644 providers/requesty/models/bedrock/claude-haiku-4-5@eu-north-1.toml create mode 100644 providers/requesty/models/bedrock/claude-haiku-4-5@eu-west-1.toml create mode 100644 providers/requesty/models/bedrock/claude-haiku-4-5@eu-west-3.toml create mode 100644 providers/requesty/models/bedrock/claude-haiku-4-5@us-east-1.toml create mode 100644 providers/requesty/models/bedrock/claude-haiku-4-5@us-east-2.toml create mode 100644 providers/requesty/models/bedrock/claude-haiku-4-5@us-west-2.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-5.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-5@eu-central-1.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-5@eu-north-1.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-5@eu-west-1.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-5@eu-west-3.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-5@us-east-1.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-5@us-east-2.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-5@us-west-2.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-6.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-7.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-7@eu-central-1.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-7@eu-north-1.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-7@eu-west-1.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-7@eu-west-3.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-8.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-8@ap-northeast-1.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-8@eu-central-1.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-8@eu-north-1.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-8@eu-west-1.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-4-8@eu-west-3.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-5.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-5@ap-northeast-1.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-5@eu-central-1.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-5@eu-north-1.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-5@eu-west-1.toml create mode 100644 providers/requesty/models/bedrock/claude-opus-5@eu-west-3.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-5.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-5@eu-central-1.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-5@eu-north-1.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-5@eu-west-1.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-5@eu-west-3.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-5@us-east-1.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-5@us-east-2.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-5@us-west-2.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-6.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-6@ap-northeast-1.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-6@eu-central-1.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-6@eu-north-1.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-6@eu-west-1.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-6@eu-west-3.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-6@us-east-1.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-6@us-east-2.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-4-6@us-west-2.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-5.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-5@ap-southeast-2.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-5@eu-central-1.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-5@eu-north-1.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-5@eu-west-1.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-5@eu-west-2.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-5@us-east-1.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-5@us-east-2.toml create mode 100644 providers/requesty/models/bedrock/claude-sonnet-5@us-west-2.toml create mode 100644 providers/requesty/models/bedrock/gpt-5.4@us-east-1.toml create mode 100644 providers/requesty/models/bedrock/gpt-5.4@us-east-2.toml create mode 100644 providers/requesty/models/bedrock/gpt-5.4@us-west-2.toml create mode 100644 providers/requesty/models/bedrock/gpt-5.5@us-east-1.toml create mode 100644 providers/requesty/models/bedrock/gpt-5.5@us-east-2.toml create mode 100644 providers/requesty/models/bedrock/kimi-k2.5@eu-north-1.toml create mode 100644 providers/requesty/models/bedrock/kimi-k2.5@eu-west-2.toml create mode 100644 providers/requesty/models/bedrock/kimi-k2.5@us-east-1.toml create mode 100644 providers/requesty/models/bedrock/kimi-k2.5@us-east-2.toml create mode 100644 providers/requesty/models/bedrock/kimi-k2.5@us-west-2.toml create mode 100644 providers/requesty/models/bedrock/minimax-m2.5@eu-central-1.toml create mode 100644 providers/requesty/models/bedrock/minimax-m2.5@eu-north-1.toml create mode 100644 providers/requesty/models/bedrock/minimax-m2.5@eu-south-1.toml create mode 100644 providers/requesty/models/bedrock/minimax-m2.5@eu-west-1.toml create mode 100644 providers/requesty/models/bedrock/minimax-m2.5@us-east-1.toml create mode 100644 providers/requesty/models/bedrock/minimax-m2.5@us-east-2.toml create mode 100644 providers/requesty/models/bedrock/minimax-m2.5@us-west-2.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-flash.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-flash@europe-central2.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-flash@europe-north1.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-flash@europe-west1.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-flash@europe-west4.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-flash@europe-west8.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-flash@us-central1.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-flash@us-east1.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-flash@us-east5.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-flash@us-south1.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-flash@us-west1.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-pro.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-pro@europe-central2.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-pro@europe-north1.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-pro@europe-west1.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-pro@europe-west4.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-pro@europe-west8.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-pro@us-central1.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-pro@us-east1.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-pro@us-east5.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-pro@us-south1.toml create mode 100644 providers/requesty/models/coding/gemini-2.5-pro@us-west1.toml create mode 100644 providers/requesty/models/deepinfra/Qwen/Qwen3-235B-A22B.toml create mode 100644 providers/requesty/models/deepinfra/Qwen/Qwen3-32B.toml create mode 100644 providers/requesty/models/deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct.toml create mode 100644 providers/requesty/models/deepinfra/Qwen/Qwen3-Max.toml create mode 100644 providers/requesty/models/deepinfra/Qwen/Qwen3.5-27B.toml create mode 100644 providers/requesty/models/deepinfra/Qwen/Qwen3.5-35B-A3B.toml create mode 100644 providers/requesty/models/deepinfra/Qwen/Qwen3.5-397B-A17B.toml create mode 100644 providers/requesty/models/deepinfra/XiaomiMiMo/MiMo-V2.5-Pro.toml create mode 100644 providers/requesty/models/deepinfra/XiaomiMiMo/MiMo-V2.5.toml create mode 100644 providers/requesty/models/deepinfra/deepseek-ai/DeepSeek-R1.toml create mode 100644 providers/requesty/models/deepinfra/deepseek-ai/DeepSeek-V4-Flash.toml create mode 100644 providers/requesty/models/deepinfra/deepseek-ai/DeepSeek-V4-Pro.toml create mode 100644 providers/requesty/models/deepinfra/google/gemma-4-26B-A4B-it.toml create mode 100644 providers/requesty/models/deepinfra/google/gemma-4-31B-it.toml create mode 100644 providers/requesty/models/deepinfra/meta-llama/Llama-3.3-70B-Instruct.toml create mode 100644 providers/requesty/models/deepinfra/moonshotai/Kimi-K2.6.toml create mode 100644 providers/requesty/models/deepinfra/nvidia/Nemotron-3-Nano-30B-A3B.toml create mode 100644 providers/requesty/models/deepinfra/zai-org/GLM-4.5-Air.toml create mode 100644 providers/requesty/models/deepinfra/zai-org/GLM-4.5.toml create mode 100644 providers/requesty/models/deepinfra/zai-org/GLM-5.1.toml create mode 100644 providers/requesty/models/deepseek/deepseek-chat.toml create mode 100644 providers/requesty/models/deepseek/deepseek-reasoner.toml create mode 100644 providers/requesty/models/deepseek/deepseek-v4-flash.toml create mode 100644 providers/requesty/models/deepseek/deepseek-v4-pro.toml create mode 100644 providers/requesty/models/doubleword/deepseek-v4-flash.toml create mode 100644 providers/requesty/models/doubleword/deepseek-v4-flash:flex.toml create mode 100644 providers/requesty/models/doubleword/deepseek-v4-pro.toml create mode 100644 providers/requesty/models/doubleword/deepseek-v4-pro:flex.toml create mode 100644 providers/requesty/models/doubleword/glm-5.2.toml create mode 100644 providers/requesty/models/doubleword/glm-5.2:flex.toml create mode 100644 providers/requesty/models/fireworks/deepseek-v4-flash.toml create mode 100644 providers/requesty/models/fireworks/deepseek-v4-pro.toml create mode 100644 providers/requesty/models/fireworks/glm-5.1.toml create mode 100644 providers/requesty/models/fireworks/glm-5.2.toml create mode 100644 providers/requesty/models/fireworks/gpt-oss-120b.toml create mode 100644 providers/requesty/models/fireworks/gpt-oss-20b.toml create mode 100644 providers/requesty/models/fireworks/kimi-k2.6.toml create mode 100644 providers/requesty/models/fireworks/kimi-k2.7-code.toml create mode 100644 providers/requesty/models/fireworks/kimi-k3.toml create mode 100644 providers/requesty/models/fireworks/minimax-m2.7.toml create mode 100644 providers/requesty/models/fireworks/minimax-m3.toml create mode 100644 providers/requesty/models/fireworks/qwen3.7-plus.toml create mode 100644 providers/requesty/models/google/gemini-2.5-flash-lite.toml create mode 100644 providers/requesty/models/google/gemini-3.1-flash-image.toml create mode 100644 providers/requesty/models/google/gemini-3.1-flash-lite.toml create mode 100644 providers/requesty/models/google/gemini-3.1-pro-preview.toml create mode 100644 providers/requesty/models/google/gemma-4-31b-it.toml create mode 100644 providers/requesty/models/groq/openai/gpt-oss-120b.toml create mode 100644 providers/requesty/models/groq/openai/gpt-oss-20b.toml create mode 100644 providers/requesty/models/inceptron/glm-5.2.toml create mode 100644 providers/requesty/models/inceptron/kimi-k2.6.toml create mode 100644 providers/requesty/models/inceptron/kimi-k2.7-Code.toml create mode 100644 providers/requesty/models/inceptron/minimax-m2.5.toml create mode 100644 providers/requesty/models/minimaxi/minimax-m2.5-highspeed.toml create mode 100644 providers/requesty/models/minimaxi/minimax-m2.5.toml create mode 100644 providers/requesty/models/minimaxi/minimax-m2.7-highspeed.toml create mode 100644 providers/requesty/models/minimaxi/minimax-m2.7.toml create mode 100644 providers/requesty/models/minimaxi/minimax-m2.toml create mode 100644 providers/requesty/models/minimaxi/minimax-m3.toml create mode 100644 providers/requesty/models/mistral/codestral-latest.toml create mode 100644 providers/requesty/models/mistral/mistral-large-latest.toml create mode 100644 providers/requesty/models/mistral/mistral-medium-latest.toml create mode 100644 providers/requesty/models/mistral/mistral-small-2603.toml create mode 100644 providers/requesty/models/mistral/mistral-small-latest.toml create mode 100644 providers/requesty/models/moonshot/kimi-k2.5.toml create mode 100644 providers/requesty/models/moonshot/kimi-k2.6.toml create mode 100644 providers/requesty/models/moonshot/kimi-k2.7-code.toml create mode 100644 providers/requesty/models/moonshot/kimi-k3.toml create mode 100644 providers/requesty/models/nebius/deepseek-ai/deepseek-v4-pro.toml create mode 100644 providers/requesty/models/nebius/glm-5.2.toml create mode 100644 providers/requesty/models/nebius/kimi-k3.toml create mode 100644 providers/requesty/models/nebius/meta-llama/Llama-3.3-70B-Instruct.toml create mode 100644 providers/requesty/models/nebius/minimaxi/minimax-m2.5.toml create mode 100644 providers/requesty/models/nebius/moonshotai/kimi-k2.6.toml create mode 100644 providers/requesty/models/nebius/nvidia/nemotron-3-super-120b-a12b.toml create mode 100644 providers/requesty/models/nebius/nvidia/nemotron-3-ultra-550b-a55b.toml create mode 100644 providers/requesty/models/nebius/openai/gpt-oss-120b.toml create mode 100644 providers/requesty/models/nebius/qwen/qwen3-32b.toml create mode 100644 providers/requesty/models/nebius/qwen/qwen3-next-80b-a3b-thinking.toml create mode 100644 providers/requesty/models/nebius/qwen/qwen3.5-397b-a17b.toml create mode 100644 providers/requesty/models/nebius/zai-org/glm-5.1.toml create mode 100644 providers/requesty/models/novita/GLM-5.toml create mode 100644 providers/requesty/models/novita/deepseek/deepseek-r1.toml create mode 100644 providers/requesty/models/novita/deepseek/deepseek-v4-flash.toml create mode 100644 providers/requesty/models/novita/google/gemma-4-26b-a4b-it.toml create mode 100644 providers/requesty/models/novita/meta-llama/llama-3.3-70b-instruct.toml create mode 100644 providers/requesty/models/novita/minimax/minimax-m2.7-highspeed.toml create mode 100644 providers/requesty/models/novita/minimax/minimax-m2.7.toml create mode 100644 providers/requesty/models/novita/mistralai/mistral-nemo.toml create mode 100644 providers/requesty/models/novita/qwen/qwen3.5-397b-a17b.toml create mode 100644 providers/requesty/models/novita/stepfun/step-3.7-flash.toml create mode 100644 providers/requesty/models/novita/tencent/hy3.toml create mode 100644 providers/requesty/models/novita/zai-org/glm-4.6.toml create mode 100644 providers/requesty/models/novita/zai-org/glm-5.1.toml create mode 100644 providers/requesty/models/nvidia/nemotron-3-nano-30b-a3b.toml create mode 100644 providers/requesty/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning.toml create mode 100644 providers/requesty/models/nvidia/nemotron-3-super-120b-a12b.toml create mode 100644 providers/requesty/models/nvidia/nemotron-3-ultra-550b-a55b.toml create mode 100644 providers/requesty/models/nvidia/nemotron-3.5-content-safety.toml create mode 100644 providers/requesty/models/openai-responses/gpt-4.1-mini.toml create mode 100644 providers/requesty/models/openai-responses/gpt-4.1-nano.toml create mode 100644 providers/requesty/models/openai-responses/gpt-4.1.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5-codex.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5-mini.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5-nano.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5-pro.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5.1-codex.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5.1.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5.2-codex.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5.2.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5.3-codex.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5.4-mini.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5.4-nano.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5.4-pro.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5.4.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5.5-pro.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5.5.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5.6-luna.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5.6-sol.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5.6-terra.toml create mode 100644 providers/requesty/models/openai-responses/gpt-5.toml create mode 100644 providers/requesty/models/openai-responses/o3-mini.toml create mode 100644 providers/requesty/models/openai-responses/o3-pro.toml create mode 100644 providers/requesty/models/openai-responses/o4-mini.toml create mode 100644 providers/requesty/models/openai/gpt-4.1-nano.toml create mode 100644 providers/requesty/models/openai/gpt-4o-2024-05-13.toml create mode 100644 providers/requesty/models/openai/gpt-4o-2024-08-06.toml create mode 100644 providers/requesty/models/openai/gpt-4o-2024-11-20.toml create mode 100644 providers/requesty/models/openai/gpt-4o.toml delete mode 100644 providers/requesty/models/openai/gpt-5-chat.toml delete mode 100644 providers/requesty/models/openai/gpt-5-codex.toml delete mode 100644 providers/requesty/models/openai/gpt-5-image.toml create mode 100644 providers/requesty/models/openai/gpt-5-mini:flex.toml create mode 100644 providers/requesty/models/openai/gpt-5-mini:priority.toml create mode 100644 providers/requesty/models/openai/gpt-5-nano:flex.toml delete mode 100644 providers/requesty/models/openai/gpt-5-pro.toml delete mode 100644 providers/requesty/models/openai/gpt-5.1-codex-max.toml delete mode 100644 providers/requesty/models/openai/gpt-5.1-codex-mini.toml delete mode 100644 providers/requesty/models/openai/gpt-5.1-codex.toml delete mode 100644 providers/requesty/models/openai/gpt-5.2-codex.toml delete mode 100644 providers/requesty/models/openai/gpt-5.2-pro.toml delete mode 100644 providers/requesty/models/openai/gpt-5.3-codex.toml create mode 100644 providers/requesty/models/openai/gpt-5.4-mini.toml create mode 100644 providers/requesty/models/openai/gpt-5.4-nano.toml delete mode 100644 providers/requesty/models/openai/gpt-5.4-pro.toml create mode 100644 providers/requesty/models/openai/gpt-5.5.toml create mode 100644 providers/requesty/models/openai/gpt-5.6-luna.toml create mode 100644 providers/requesty/models/openai/gpt-5.6-sol.toml create mode 100644 providers/requesty/models/openai/gpt-5.6-terra.toml create mode 100644 providers/requesty/models/openai/gpt-5:flex.toml create mode 100644 providers/requesty/models/openai/gpt-5:priority.toml create mode 100644 providers/requesty/models/openai/o1.toml create mode 100644 providers/requesty/models/openai/o1:high.toml create mode 100644 providers/requesty/models/openai/o1:low.toml create mode 100644 providers/requesty/models/openai/o1:medium.toml create mode 100644 providers/requesty/models/openai/o3-mini.toml create mode 100644 providers/requesty/models/openai/o3-mini:high.toml create mode 100644 providers/requesty/models/openai/o3-mini:low.toml create mode 100644 providers/requesty/models/openai/o3-mini:medium.toml create mode 100644 providers/requesty/models/openai/o3.toml create mode 100644 providers/requesty/models/openai/o3:flex.toml create mode 100644 providers/requesty/models/openai/o4-mini:flex.toml create mode 100644 providers/requesty/models/openai/o4-mini:high.toml create mode 100644 providers/requesty/models/openai/o4-mini:low.toml create mode 100644 providers/requesty/models/openai/o4-mini:medium.toml create mode 100644 providers/requesty/models/parasail/google/gemma-4-26B-A4B-it.toml create mode 100644 providers/requesty/models/parasail/kimi-k2.7-code.toml create mode 100644 providers/requesty/models/perplexity/sonar-pro.toml create mode 100644 providers/requesty/models/perplexity/sonar-reasoning-pro.toml create mode 100644 providers/requesty/models/perplexity/sonar.toml create mode 100644 providers/requesty/models/poolside/laguna-m.1.toml create mode 100644 providers/requesty/models/poolside/laguna-xs.2.toml create mode 100644 providers/requesty/models/sakana/fugu-ultra.toml create mode 100644 providers/requesty/models/sference/deepseek-v4-flash.toml create mode 100644 providers/requesty/models/sference/glm-5.2.toml create mode 100644 providers/requesty/models/sference/kimi-k3.toml create mode 100644 providers/requesty/models/tensorx/deepseek-v4-flash.toml create mode 100644 providers/requesty/models/tensorx/deepseek-v4-pro.toml create mode 100644 providers/requesty/models/tensorx/glm-5.2.toml create mode 100644 providers/requesty/models/tensorx/kimi-k2.7-code.toml create mode 100644 providers/requesty/models/tensorx/kimi-k3.toml create mode 100644 providers/requesty/models/tensorx/minimax-m3.toml create mode 100644 providers/requesty/models/thinkingmachines/inkling.toml create mode 100644 providers/requesty/models/vertex/claude-fable-5.toml create mode 100644 providers/requesty/models/vertex/claude-fable-5@eu.toml create mode 100644 providers/requesty/models/vertex/claude-haiku-4-5.toml create mode 100644 providers/requesty/models/vertex/claude-haiku-4-5@europe-west1.toml create mode 100644 providers/requesty/models/vertex/claude-haiku-4-5@us-east5.toml create mode 100644 providers/requesty/models/vertex/claude-opus-4-1.toml create mode 100644 providers/requesty/models/vertex/claude-opus-4-1@us-east5.toml create mode 100644 providers/requesty/models/vertex/claude-opus-4-5.toml create mode 100644 providers/requesty/models/vertex/claude-opus-4-5@europe-west1.toml create mode 100644 providers/requesty/models/vertex/claude-opus-4-5@us-east5.toml create mode 100644 providers/requesty/models/vertex/claude-opus-4-6.toml create mode 100644 providers/requesty/models/vertex/claude-opus-4-6@europe-west1.toml create mode 100644 providers/requesty/models/vertex/claude-opus-4-6@us-east5.toml create mode 100644 providers/requesty/models/vertex/claude-opus-4-7.toml create mode 100644 providers/requesty/models/vertex/claude-opus-4-7@eu.toml create mode 100644 providers/requesty/models/vertex/claude-opus-4-7@us.toml create mode 100644 providers/requesty/models/vertex/claude-opus-4-8.toml create mode 100644 providers/requesty/models/vertex/claude-opus-4-8@eu.toml create mode 100644 providers/requesty/models/vertex/claude-opus-4-8@us.toml create mode 100644 providers/requesty/models/vertex/claude-opus-5.toml create mode 100644 providers/requesty/models/vertex/claude-opus-5@eu.toml create mode 100644 providers/requesty/models/vertex/claude-opus-5@us.toml create mode 100644 providers/requesty/models/vertex/claude-sonnet-4-5.toml create mode 100644 providers/requesty/models/vertex/claude-sonnet-4-5@europe-west1.toml create mode 100644 providers/requesty/models/vertex/claude-sonnet-4-5@us-east5.toml create mode 100644 providers/requesty/models/vertex/claude-sonnet-4-6.toml create mode 100644 providers/requesty/models/vertex/claude-sonnet-4-6@europe-west1.toml create mode 100644 providers/requesty/models/vertex/claude-sonnet-4-6@us-east5.toml create mode 100644 providers/requesty/models/vertex/claude-sonnet-5.toml create mode 100644 providers/requesty/models/vertex/claude-sonnet-5@eu.toml create mode 100644 providers/requesty/models/vertex/claude-sonnet-5@us.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-image.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-image@europe-central2.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-image@europe-north1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-image@europe-southwest1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-image@europe-west1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-image@europe-west4.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-image@europe-west8.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-image@us-central1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-image@us-east1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-image@us-east4.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-image@us-east5.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-image@us-south1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-image@us-west1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-image@us-west4.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-lite.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-central2.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-north1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-west1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-west4.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-west8.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-lite@us-central1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-lite@us-east1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-lite@us-east5.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-lite@us-south1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash-lite@us-west1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash@europe-central2.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash@europe-north1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash@europe-west1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash@europe-west4.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash@europe-west8.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash@us-central1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash@us-east1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash@us-east5.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash@us-south1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-flash@us-west1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-pro.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-pro@europe-central2.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-pro@europe-north1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-pro@europe-west1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-pro@europe-west4.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-pro@europe-west8.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-pro@us-central1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-pro@us-east1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-pro@us-east5.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-pro@us-south1.toml create mode 100644 providers/requesty/models/vertex/gemini-2.5-pro@us-west1.toml create mode 100644 providers/requesty/models/vertex/gemini-3-flash-preview.toml create mode 100644 providers/requesty/models/vertex/gemini-3-flash-preview:flex.toml create mode 100644 providers/requesty/models/vertex/gemini-3-pro-image.toml create mode 100644 providers/requesty/models/vertex/gemini-3-pro-preview.toml create mode 100644 providers/requesty/models/vertex/gemini-3.1-flash-image.toml create mode 100644 providers/requesty/models/vertex/gemini-3.1-flash-lite.toml create mode 100644 providers/requesty/models/vertex/gemini-3.1-flash-lite@eu.toml create mode 100644 providers/requesty/models/vertex/gemini-3.1-flash-lite@us.toml create mode 100644 providers/requesty/models/vertex/gemini-3.1-pro-preview.toml create mode 100644 providers/requesty/models/vertex/gemini-3.1-pro-preview:flex.toml create mode 100644 providers/requesty/models/vertex/gemini-3.5-flash-lite.toml create mode 100644 providers/requesty/models/vertex/gemini-3.5-flash-lite@eu.toml create mode 100644 providers/requesty/models/vertex/gemini-3.5-flash.toml create mode 100644 providers/requesty/models/vertex/gemini-3.5-flash@eu.toml create mode 100644 providers/requesty/models/vertex/gemini-3.5-flash@us.toml create mode 100644 providers/requesty/models/vertex/gemini-3.6-flash.toml create mode 100644 providers/requesty/models/xai/grok-4.3.toml create mode 100644 providers/requesty/models/xai/grok-4.5.toml create mode 100644 providers/requesty/models/xai/grok-build-0.1.toml create mode 100644 providers/requesty/models/xiaomi/mimo-v2.5-pro.toml create mode 100644 providers/requesty/models/xiaomi/mimo-v2.5.toml create mode 100644 providers/requesty/models/zai/GLM-4.5.toml create mode 100644 providers/requesty/models/zai/GLM-4.6.toml create mode 100644 providers/requesty/models/zai/GLM-4.7.toml create mode 100644 providers/requesty/models/zai/GLM-5.toml create mode 100644 providers/requesty/models/zai/glm-5.1.toml create mode 100644 providers/requesty/models/zai/glm-5.2.toml diff --git a/providers/requesty/models/alibaba/qwen-max.toml b/providers/requesty/models/alibaba/qwen-max.toml new file mode 100644 index 00000000000..41ea021fed9 --- /dev/null +++ b/providers/requesty/models/alibaba/qwen-max.toml @@ -0,0 +1,8 @@ +base_model = "alibaba/qwen-max" +structured_output = true + +[cost] +input = 1.6 +output = 6.4 +cache_read = 1.6 +cache_write = 1.6 diff --git a/providers/requesty/models/alibaba/qwen-plus.toml b/providers/requesty/models/alibaba/qwen-plus.toml new file mode 100644 index 00000000000..b53dfcc1b1e --- /dev/null +++ b/providers/requesty/models/alibaba/qwen-plus.toml @@ -0,0 +1,15 @@ +base_model = "alibaba/qwen-plus" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.4 +output = 1.2 +cache_read = 0.4 +cache_write = 0.4 + +[limit] +context = 131_072 diff --git a/providers/requesty/models/alibaba/qwen-turbo.toml b/providers/requesty/models/alibaba/qwen-turbo.toml new file mode 100644 index 00000000000..850f64effcb --- /dev/null +++ b/providers/requesty/models/alibaba/qwen-turbo.toml @@ -0,0 +1,12 @@ +base_model = "alibaba/qwen-turbo" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.05 +output = 0.2 +cache_read = 0.05 +cache_write = 0.05 diff --git a/providers/requesty/models/alibaba/qwen3-coder-flash.toml b/providers/requesty/models/alibaba/qwen3-coder-flash.toml new file mode 100644 index 00000000000..159c6aea68b --- /dev/null +++ b/providers/requesty/models/alibaba/qwen3-coder-flash.toml @@ -0,0 +1,11 @@ +base_model = "alibaba/qwen3-coder-flash" +structured_output = true + +[cost] +input = 0.3 +output = 1.5 +cache_read = 0.08 +cache_write = 0.3 + +[limit] +context = 1_048_576 diff --git a/providers/requesty/models/alibaba/qwen3-coder-plus.toml b/providers/requesty/models/alibaba/qwen3-coder-plus.toml new file mode 100644 index 00000000000..f6075e47f4c --- /dev/null +++ b/providers/requesty/models/alibaba/qwen3-coder-plus.toml @@ -0,0 +1,6 @@ +base_model = "alibaba/qwen3-coder-plus" +structured_output = true + +[cost] +input = 1 +output = 5 diff --git a/providers/requesty/models/alibaba/qwen3-max.toml b/providers/requesty/models/alibaba/qwen3-max.toml new file mode 100644 index 00000000000..5f62fd9aba5 --- /dev/null +++ b/providers/requesty/models/alibaba/qwen3-max.toml @@ -0,0 +1,6 @@ +base_model = "alibaba/qwen3-max" +structured_output = true + +[cost] +input = 0.861 +output = 3.441 diff --git a/providers/requesty/models/alibaba/qwen3.6-plus.toml b/providers/requesty/models/alibaba/qwen3.6-plus.toml new file mode 100644 index 00000000000..fd7f4503468 --- /dev/null +++ b/providers/requesty/models/alibaba/qwen3.6-plus.toml @@ -0,0 +1,12 @@ +base_model = "alibaba/qwen3.6-plus" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.5 +output = 3 +cache_read = 0.05 +cache_write = 0.625 diff --git a/providers/requesty/models/alibaba/qwen3.7-max.toml b/providers/requesty/models/alibaba/qwen3.7-max.toml new file mode 100644 index 00000000000..3d9a33032f8 --- /dev/null +++ b/providers/requesty/models/alibaba/qwen3.7-max.toml @@ -0,0 +1,15 @@ +base_model = "alibaba/qwen3.7-max" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.5 +output = 7.5 +cache_read = 0.25 +cache_write = 3.125 + +[limit] +context = 1_048_576 diff --git a/providers/requesty/models/alibaba/qwen3.7-plus.toml b/providers/requesty/models/alibaba/qwen3.7-plus.toml new file mode 100644 index 00000000000..f0a5eef1e2f --- /dev/null +++ b/providers/requesty/models/alibaba/qwen3.7-plus.toml @@ -0,0 +1,16 @@ +base_model = "alibaba/qwen3.7-plus" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.32 +output = 1.28 +cache_read = 0.032 +cache_write = 0.4 + +[limit] +context = 1_048_576 +output = 65_536 diff --git a/providers/requesty/models/anthropic/claude-3-7-sonnet.toml b/providers/requesty/models/anthropic/claude-3-7-sonnet.toml deleted file mode 100644 index 625fbb97c72..00000000000 --- a/providers/requesty/models/anthropic/claude-3-7-sonnet.toml +++ /dev/null @@ -1,26 +0,0 @@ -name = "Claude Sonnet 3.7" -description = "Balanced Claude model for coding, analysis, agent workflows, and cost control" -family = "claude-sonnet" -release_date = "2025-02-19" -last_updated = "2025-02-19" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -tool_call = true -knowledge = "2024-01" -open_weights = false - -[cost] -input = 3.00 -output = 15.00 -cache_read = 0.30 -cache_write = 3.75 - -[limit] -context = 200_000 -output = 64_000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] diff --git a/providers/requesty/models/anthropic/claude-fable-5.toml b/providers/requesty/models/anthropic/claude-fable-5.toml new file mode 100644 index 00000000000..c10753af62c --- /dev/null +++ b/providers/requesty/models/anthropic/claude-fable-5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-fable-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 10 +output = 50 +cache_read = 1 +cache_write = 12.5 diff --git a/providers/requesty/models/anthropic/claude-haiku-4-5.toml b/providers/requesty/models/anthropic/claude-haiku-4-5.toml index d2238e3fb59..ff04c8ab844 100644 --- a/providers/requesty/models/anthropic/claude-haiku-4-5.toml +++ b/providers/requesty/models/anthropic/claude-haiku-4-5.toml @@ -1,26 +1,13 @@ -name = "Claude Haiku 4.5" +base_model = "anthropic/claude-haiku-4-5" description = "Fast Claude model for responsive assistance, classification, and lightweight agents" -family = "claude-haiku" -release_date = "2025-10-15" -last_updated = "2025-10-15" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -tool_call = true -knowledge = "2025-02-01" -open_weights = false +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] [cost] -input = 1.00 -output = 5.00 +input = 1 +output = 5 cache_read = 0.1 cache_write = 1.25 - -[limit] -context = 200_000 -output = 62_000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] diff --git a/providers/requesty/models/anthropic/claude-opus-4-1.toml b/providers/requesty/models/anthropic/claude-opus-4-1.toml index e98d82bf652..c193c90d2a8 100644 --- a/providers/requesty/models/anthropic/claude-opus-4-1.toml +++ b/providers/requesty/models/anthropic/claude-opus-4-1.toml @@ -1,6 +1,9 @@ base_model = "anthropic/claude-opus-4-1-20250805" +structured_output = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] [cost] input = 15 diff --git a/providers/requesty/models/anthropic/claude-opus-4-5.toml b/providers/requesty/models/anthropic/claude-opus-4-5.toml index 8710c9a3c7b..ece5338de62 100644 --- a/providers/requesty/models/anthropic/claude-opus-4-5.toml +++ b/providers/requesty/models/anthropic/claude-opus-4-5.toml @@ -1,26 +1,13 @@ -name = "Claude Opus 4.5" +base_model = "anthropic/claude-opus-4-5" description = "Flagship Claude model for deep reasoning, coding, and long-horizon agents" -family = "claude-opus" -release_date = "2025-11-24" -last_updated = "2025-11-24" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -tool_call = true -knowledge = "2025-03-31" -open_weights = false +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] [cost] -input = 5.00 -output = 25.00 +input = 5 +output = 25 cache_read = 0.5 cache_write = 6.25 - -[limit] -context = 200_000 -output = 64_000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] diff --git a/providers/requesty/models/anthropic/claude-opus-4-6.toml b/providers/requesty/models/anthropic/claude-opus-4-6.toml index 18e8da67372..46e74c75fdb 100644 --- a/providers/requesty/models/anthropic/claude-opus-4-6.toml +++ b/providers/requesty/models/anthropic/claude-opus-4-6.toml @@ -1,34 +1,20 @@ -name = "Claude Opus 4.6" +base_model = "anthropic/claude-opus-4-6" description = "Flagship Claude model for deep reasoning, coding, and long-horizon agents" -family = "claude-opus" -release_date = "2026-02-05" -last_updated = "2026-02-05" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -tool_call = true structured_output = true -knowledge = "2025-05-31" -open_weights = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] [cost] -input = 5.00 -output = 25.00 -cache_read = 0.50 +input = 5 +output = 25 +cache_read = 0.5 cache_write = 6.25 [[cost.tiers]] -tier = { size = 200_000 } -input = 10.00 -output = 37.50 -cache_read = 1.00 -cache_write = 12.50 - -[limit] -context = 1_000_000 -output = 128_000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] +tier = { type = "context", size = 200_000 } +input = 10 +output = 37.5 +cache_read = 1 +cache_write = 12.5 diff --git a/providers/requesty/models/anthropic/claude-opus-4-7.toml b/providers/requesty/models/anthropic/claude-opus-4-7.toml new file mode 100644 index 00000000000..4edff5914b5 --- /dev/null +++ b/providers/requesty/models/anthropic/claude-opus-4-7.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-7" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 25 +cache_read = 0.5 +cache_write = 6.25 diff --git a/providers/requesty/models/anthropic/claude-opus-4-8.toml b/providers/requesty/models/anthropic/claude-opus-4-8.toml new file mode 100644 index 00000000000..d5cf84bf456 --- /dev/null +++ b/providers/requesty/models/anthropic/claude-opus-4-8.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-8" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 25 +cache_read = 0.5 +cache_write = 6.25 diff --git a/providers/requesty/models/anthropic/claude-opus-4.toml b/providers/requesty/models/anthropic/claude-opus-4.toml deleted file mode 100644 index 7f9f31eef77..00000000000 --- a/providers/requesty/models/anthropic/claude-opus-4.toml +++ /dev/null @@ -1,26 +0,0 @@ -name = "Claude Opus 4" -description = "Flagship Claude model for deep reasoning, coding, and long-horizon agents" -family = "claude-opus" -release_date = "2025-05-22" -last_updated = "2025-05-22" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -tool_call = true -knowledge = "2025-03-31" -open_weights = false - -[cost] -input = 15.00 -output = 75.00 -cache_read = 1.50 -cache_write = 18.75 - -[limit] -context = 200_000 -output = 32_000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] diff --git a/providers/requesty/models/anthropic/claude-opus-5.toml b/providers/requesty/models/anthropic/claude-opus-5.toml new file mode 100644 index 00000000000..143e01133a7 --- /dev/null +++ b/providers/requesty/models/anthropic/claude-opus-5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 25 +cache_read = 0.5 +cache_write = 6.25 diff --git a/providers/requesty/models/anthropic/claude-sonnet-4-5.toml b/providers/requesty/models/anthropic/claude-sonnet-4-5.toml index 612054daadb..008fefd271a 100644 --- a/providers/requesty/models/anthropic/claude-sonnet-4-5.toml +++ b/providers/requesty/models/anthropic/claude-sonnet-4-5.toml @@ -1,6 +1,9 @@ base_model = "anthropic/claude-sonnet-4-5-20250929" +structured_output = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] [cost] input = 3 diff --git a/providers/requesty/models/anthropic/claude-sonnet-4-6.toml b/providers/requesty/models/anthropic/claude-sonnet-4-6.toml index 186b6d51c47..8a348912d2f 100644 --- a/providers/requesty/models/anthropic/claude-sonnet-4-6.toml +++ b/providers/requesty/models/anthropic/claude-sonnet-4-6.toml @@ -1,34 +1,20 @@ -name = "Claude Sonnet 4.6" +base_model = "anthropic/claude-sonnet-4-6" description = "Balanced Claude model for coding, analysis, agent workflows, and cost control" -family = "claude-sonnet" -release_date = "2026-02-17" -last_updated = "2026-02-17" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -tool_call = true structured_output = true -knowledge = "2025-08-31" -open_weights = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] [cost] -input = 3.00 -output = 15.00 -cache_read = 0.30 +input = 3 +output = 15 +cache_read = 0.3 cache_write = 3.75 [[cost.tiers]] -tier = { size = 200_000 } -input = 6.00 -output = 22.50 -cache_read = 0.60 -cache_write = 7.50 - -[limit] -context = 1_000_000 -output = 128_000 - -[modalities] -input = ["text", "image"] -output = ["text"] +tier = { type = "context", size = 200_000 } +input = 6 +output = 22.5 +cache_read = 0.6 +cache_write = 7.5 diff --git a/providers/requesty/models/anthropic/claude-sonnet-4.toml b/providers/requesty/models/anthropic/claude-sonnet-4.toml deleted file mode 100644 index eb05dd8979c..00000000000 --- a/providers/requesty/models/anthropic/claude-sonnet-4.toml +++ /dev/null @@ -1,9 +0,0 @@ -base_model = "anthropic/claude-sonnet-4-20250514" - -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] - -[cost] -input = 3 -output = 15 -cache_read = 0.3 -cache_write = 3.75 diff --git a/providers/requesty/models/anthropic/claude-sonnet-5.toml b/providers/requesty/models/anthropic/claude-sonnet-5.toml new file mode 100644 index 00000000000..6f4bad93f23 --- /dev/null +++ b/providers/requesty/models/anthropic/claude-sonnet-5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2 +output = 10 +cache_read = 0.2 +cache_write = 2.5 diff --git a/providers/requesty/models/azure/gpt-4.1-mini@eastus2.toml b/providers/requesty/models/azure/gpt-4.1-mini@eastus2.toml new file mode 100644 index 00000000000..b2d9217542d --- /dev/null +++ b/providers/requesty/models/azure/gpt-4.1-mini@eastus2.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1-mini" + +[cost] +input = 0.4 +output = 1.6 +cache_read = 0.1 diff --git a/providers/requesty/models/azure/gpt-4.1-mini@francecentral.toml b/providers/requesty/models/azure/gpt-4.1-mini@francecentral.toml new file mode 100644 index 00000000000..42eba8b8f9c --- /dev/null +++ b/providers/requesty/models/azure/gpt-4.1-mini@francecentral.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1-mini" + +[cost] +input = 0.44 +output = 1.76 +cache_read = 0.11 diff --git a/providers/requesty/models/azure/gpt-4.1-mini@uksouth.toml b/providers/requesty/models/azure/gpt-4.1-mini@uksouth.toml new file mode 100644 index 00000000000..42eba8b8f9c --- /dev/null +++ b/providers/requesty/models/azure/gpt-4.1-mini@uksouth.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1-mini" + +[cost] +input = 0.44 +output = 1.76 +cache_read = 0.11 diff --git a/providers/requesty/models/azure/gpt-4.1-mini@westus3.toml b/providers/requesty/models/azure/gpt-4.1-mini@westus3.toml new file mode 100644 index 00000000000..b2d9217542d --- /dev/null +++ b/providers/requesty/models/azure/gpt-4.1-mini@westus3.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1-mini" + +[cost] +input = 0.4 +output = 1.6 +cache_read = 0.1 diff --git a/providers/requesty/models/azure/gpt-4.1-nano.toml b/providers/requesty/models/azure/gpt-4.1-nano.toml new file mode 100644 index 00000000000..f85c0947701 --- /dev/null +++ b/providers/requesty/models/azure/gpt-4.1-nano.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1-nano" + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.025 diff --git a/providers/requesty/models/azure/gpt-4.1-nano@eastus2.toml b/providers/requesty/models/azure/gpt-4.1-nano@eastus2.toml new file mode 100644 index 00000000000..47654e6eee2 --- /dev/null +++ b/providers/requesty/models/azure/gpt-4.1-nano@eastus2.toml @@ -0,0 +1,11 @@ +base_model = "openai/gpt-4.1-nano" +reasoning = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.025 diff --git a/providers/requesty/models/azure/gpt-4.1-nano@francecentral.toml b/providers/requesty/models/azure/gpt-4.1-nano@francecentral.toml new file mode 100644 index 00000000000..04fc3e5253f --- /dev/null +++ b/providers/requesty/models/azure/gpt-4.1-nano@francecentral.toml @@ -0,0 +1,11 @@ +base_model = "openai/gpt-4.1-nano" +reasoning = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.11 +output = 0.44 +cache_read = 0.0275 diff --git a/providers/requesty/models/azure/gpt-4.1-nano@swedencentral.toml b/providers/requesty/models/azure/gpt-4.1-nano@swedencentral.toml new file mode 100644 index 00000000000..04fc3e5253f --- /dev/null +++ b/providers/requesty/models/azure/gpt-4.1-nano@swedencentral.toml @@ -0,0 +1,11 @@ +base_model = "openai/gpt-4.1-nano" +reasoning = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.11 +output = 0.44 +cache_read = 0.0275 diff --git a/providers/requesty/models/azure/gpt-4.1-nano@uksouth.toml b/providers/requesty/models/azure/gpt-4.1-nano@uksouth.toml new file mode 100644 index 00000000000..04fc3e5253f --- /dev/null +++ b/providers/requesty/models/azure/gpt-4.1-nano@uksouth.toml @@ -0,0 +1,11 @@ +base_model = "openai/gpt-4.1-nano" +reasoning = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.11 +output = 0.44 +cache_read = 0.0275 diff --git a/providers/requesty/models/azure/gpt-4.1-nano@westus3.toml b/providers/requesty/models/azure/gpt-4.1-nano@westus3.toml new file mode 100644 index 00000000000..47654e6eee2 --- /dev/null +++ b/providers/requesty/models/azure/gpt-4.1-nano@westus3.toml @@ -0,0 +1,11 @@ +base_model = "openai/gpt-4.1-nano" +reasoning = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.025 diff --git a/providers/requesty/models/azure/gpt-4.1.toml b/providers/requesty/models/azure/gpt-4.1.toml new file mode 100644 index 00000000000..1fdb518f628 --- /dev/null +++ b/providers/requesty/models/azure/gpt-4.1.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1" + +[cost] +input = 2 +output = 8 +cache_read = 0.5 diff --git a/providers/requesty/models/azure/gpt-4.1@eastus2.toml b/providers/requesty/models/azure/gpt-4.1@eastus2.toml new file mode 100644 index 00000000000..1fdb518f628 --- /dev/null +++ b/providers/requesty/models/azure/gpt-4.1@eastus2.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1" + +[cost] +input = 2 +output = 8 +cache_read = 0.5 diff --git a/providers/requesty/models/azure/gpt-4.1@francecentral.toml b/providers/requesty/models/azure/gpt-4.1@francecentral.toml new file mode 100644 index 00000000000..7ee4f7b59ac --- /dev/null +++ b/providers/requesty/models/azure/gpt-4.1@francecentral.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1" + +[cost] +input = 2.2 +output = 8.8 +cache_read = 0.55 diff --git a/providers/requesty/models/azure/gpt-4.1@swedencentral.toml b/providers/requesty/models/azure/gpt-4.1@swedencentral.toml new file mode 100644 index 00000000000..7ee4f7b59ac --- /dev/null +++ b/providers/requesty/models/azure/gpt-4.1@swedencentral.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1" + +[cost] +input = 2.2 +output = 8.8 +cache_read = 0.55 diff --git a/providers/requesty/models/azure/gpt-4.1@uksouth.toml b/providers/requesty/models/azure/gpt-4.1@uksouth.toml new file mode 100644 index 00000000000..7ee4f7b59ac --- /dev/null +++ b/providers/requesty/models/azure/gpt-4.1@uksouth.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1" + +[cost] +input = 2.2 +output = 8.8 +cache_read = 0.55 diff --git a/providers/requesty/models/azure/gpt-4.1@westus3.toml b/providers/requesty/models/azure/gpt-4.1@westus3.toml new file mode 100644 index 00000000000..1fdb518f628 --- /dev/null +++ b/providers/requesty/models/azure/gpt-4.1@westus3.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1" + +[cost] +input = 2 +output = 8 +cache_read = 0.5 diff --git a/providers/requesty/models/azure/gpt-4o-mini@eastus2.toml b/providers/requesty/models/azure/gpt-4o-mini@eastus2.toml new file mode 100644 index 00000000000..1ccd45052ac --- /dev/null +++ b/providers/requesty/models/azure/gpt-4o-mini@eastus2.toml @@ -0,0 +1,9 @@ +base_model = "openai/gpt-4o-mini" + +[cost] +input = 0.15 +output = 0.6 +cache_read = 0.075 + +[limit] +output = 16_000 diff --git a/providers/requesty/models/azure/gpt-4o-mini@swedencentral.toml b/providers/requesty/models/azure/gpt-4o-mini@swedencentral.toml new file mode 100644 index 00000000000..ea4f37ee7a5 --- /dev/null +++ b/providers/requesty/models/azure/gpt-4o-mini@swedencentral.toml @@ -0,0 +1,9 @@ +base_model = "openai/gpt-4o-mini" + +[cost] +input = 0.165 +output = 0.66 +cache_read = 0.0825 + +[limit] +output = 16_000 diff --git a/providers/requesty/models/azure/gpt-5-mini.toml b/providers/requesty/models/azure/gpt-5-mini.toml new file mode 100644 index 00000000000..2abe12409d8 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5-mini.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5-mini" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.25 +output = 2 +cache_read = 0.025 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5-mini@eastus2.toml b/providers/requesty/models/azure/gpt-5-mini@eastus2.toml new file mode 100644 index 00000000000..2abe12409d8 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5-mini@eastus2.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5-mini" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.25 +output = 2 +cache_read = 0.025 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5-mini@francecentral.toml b/providers/requesty/models/azure/gpt-5-mini@francecentral.toml new file mode 100644 index 00000000000..92f9714c842 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5-mini@francecentral.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5-mini" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.275 +output = 2.2 +cache_read = 0.0275 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5-mini@swedencentral.toml b/providers/requesty/models/azure/gpt-5-mini@swedencentral.toml new file mode 100644 index 00000000000..92f9714c842 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5-mini@swedencentral.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5-mini" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.275 +output = 2.2 +cache_read = 0.0275 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5-mini@uksouth.toml b/providers/requesty/models/azure/gpt-5-mini@uksouth.toml new file mode 100644 index 00000000000..92f9714c842 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5-mini@uksouth.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5-mini" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.275 +output = 2.2 +cache_read = 0.0275 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5-nano.toml b/providers/requesty/models/azure/gpt-5-nano.toml new file mode 100644 index 00000000000..43a824bbd2e --- /dev/null +++ b/providers/requesty/models/azure/gpt-5-nano.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5-nano" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.05 +output = 0.4 +cache_read = 0.005 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5-nano@eastus2.toml b/providers/requesty/models/azure/gpt-5-nano@eastus2.toml new file mode 100644 index 00000000000..43a824bbd2e --- /dev/null +++ b/providers/requesty/models/azure/gpt-5-nano@eastus2.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5-nano" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.05 +output = 0.4 +cache_read = 0.005 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5-nano@francecentral.toml b/providers/requesty/models/azure/gpt-5-nano@francecentral.toml new file mode 100644 index 00000000000..de4f62a8aa7 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5-nano@francecentral.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5-nano" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.055 +output = 0.44 +cache_read = 0.0055 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5-nano@swedencentral.toml b/providers/requesty/models/azure/gpt-5-nano@swedencentral.toml new file mode 100644 index 00000000000..de4f62a8aa7 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5-nano@swedencentral.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5-nano" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.055 +output = 0.44 +cache_read = 0.0055 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5.1.toml b/providers/requesty/models/azure/gpt-5.1.toml new file mode 100644 index 00000000000..6a4750fbe44 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.1.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5.1" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.125 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5.1@eastus2.toml b/providers/requesty/models/azure/gpt-5.1@eastus2.toml new file mode 100644 index 00000000000..6a4750fbe44 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.1@eastus2.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5.1" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.125 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5.1@francecentral.toml b/providers/requesty/models/azure/gpt-5.1@francecentral.toml new file mode 100644 index 00000000000..3e098d7b6e1 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.1@francecentral.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5.1" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.375 +output = 11 +cache_read = 0.1375 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5.1@swedencentral.toml b/providers/requesty/models/azure/gpt-5.1@swedencentral.toml new file mode 100644 index 00000000000..3e098d7b6e1 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.1@swedencentral.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5.1" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.375 +output = 11 +cache_read = 0.1375 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5.2-codex@eastus2.toml b/providers/requesty/models/azure/gpt-5.2-codex@eastus2.toml new file mode 100644 index 00000000000..f86e1c0d4ae --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.2-codex@eastus2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.2-codex" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.75 +output = 14 +cache_read = 0.175 diff --git a/providers/requesty/models/azure/gpt-5.2@eastus2.toml b/providers/requesty/models/azure/gpt-5.2@eastus2.toml new file mode 100644 index 00000000000..f5b3e03830a --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.2@eastus2.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5.2" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.75 +output = 14 +cache_read = 0.175 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5.3-codex@eastus2.toml b/providers/requesty/models/azure/gpt-5.3-codex@eastus2.toml new file mode 100644 index 00000000000..2cd5a8d5b71 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.3-codex@eastus2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.3-codex" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.75 +output = 14 +cache_read = 0.175 diff --git a/providers/requesty/models/azure/gpt-5.4-mini.toml b/providers/requesty/models/azure/gpt-5.4-mini.toml new file mode 100644 index 00000000000..be3542d6282 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.4-mini.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.75 +output = 4.5 +cache_read = 0.075 diff --git a/providers/requesty/models/azure/gpt-5.4-mini@eastus2.toml b/providers/requesty/models/azure/gpt-5.4-mini@eastus2.toml new file mode 100644 index 00000000000..be3542d6282 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.4-mini@eastus2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.75 +output = 4.5 +cache_read = 0.075 diff --git a/providers/requesty/models/azure/gpt-5.4.toml b/providers/requesty/models/azure/gpt-5.4.toml new file mode 100644 index 00000000000..bceb46dba86 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.4.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.5 +output = 15 +cache_read = 0.25 diff --git a/providers/requesty/models/azure/gpt-5.4@eastus2.toml b/providers/requesty/models/azure/gpt-5.4@eastus2.toml new file mode 100644 index 00000000000..bceb46dba86 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.4@eastus2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.5 +output = 15 +cache_read = 0.25 diff --git a/providers/requesty/models/azure/gpt-5.4@francecentral.toml b/providers/requesty/models/azure/gpt-5.4@francecentral.toml new file mode 100644 index 00000000000..bceb46dba86 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.4@francecentral.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.5 +output = 15 +cache_read = 0.25 diff --git a/providers/requesty/models/azure/gpt-5.4@swedencentral.toml b/providers/requesty/models/azure/gpt-5.4@swedencentral.toml new file mode 100644 index 00000000000..bceb46dba86 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.4@swedencentral.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.5 +output = 15 +cache_read = 0.25 diff --git a/providers/requesty/models/azure/gpt-5.5@eastus2.toml b/providers/requesty/models/azure/gpt-5.5@eastus2.toml new file mode 100644 index 00000000000..b36d2d62074 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.5@eastus2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 30 +cache_read = 0.5 diff --git a/providers/requesty/models/azure/gpt-5.5@swedencentral.toml b/providers/requesty/models/azure/gpt-5.5@swedencentral.toml new file mode 100644 index 00000000000..b36d2d62074 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.5@swedencentral.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 30 +cache_read = 0.5 diff --git a/providers/requesty/models/azure/gpt-5.6-luna@eastus2.toml b/providers/requesty/models/azure/gpt-5.6-luna@eastus2.toml new file mode 100644 index 00000000000..08a1a8839f0 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.6-luna@eastus2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-luna" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1 +output = 6 +cache_read = 0.1 diff --git a/providers/requesty/models/azure/gpt-5.6-luna@swedencentral.toml b/providers/requesty/models/azure/gpt-5.6-luna@swedencentral.toml new file mode 100644 index 00000000000..5c3dc10ee84 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.6-luna@swedencentral.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-luna" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 6.6 +cache_read = 0.11 diff --git a/providers/requesty/models/azure/gpt-5.6-sol@eastus2.toml b/providers/requesty/models/azure/gpt-5.6-sol@eastus2.toml new file mode 100644 index 00000000000..edccc583108 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.6-sol@eastus2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-sol" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 30 +cache_read = 0.5 diff --git a/providers/requesty/models/azure/gpt-5.6-sol@swedencentral.toml b/providers/requesty/models/azure/gpt-5.6-sol@swedencentral.toml new file mode 100644 index 00000000000..dd1a19c3fb9 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.6-sol@swedencentral.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-sol" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 33 +cache_read = 0.55 diff --git a/providers/requesty/models/azure/gpt-5.6-terra@eastus2.toml b/providers/requesty/models/azure/gpt-5.6-terra@eastus2.toml new file mode 100644 index 00000000000..714e3afa796 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.6-terra@eastus2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-terra" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.5 +output = 15 +cache_read = 0.25 diff --git a/providers/requesty/models/azure/gpt-5.6-terra@swedencentral.toml b/providers/requesty/models/azure/gpt-5.6-terra@swedencentral.toml new file mode 100644 index 00000000000..7dbc894119a --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.6-terra@swedencentral.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-terra" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.75 +output = 16.5 +cache_read = 0.275 diff --git a/providers/requesty/models/azure/gpt-5.toml b/providers/requesty/models/azure/gpt-5.toml new file mode 100644 index 00000000000..60c1714a76a --- /dev/null +++ b/providers/requesty/models/azure/gpt-5.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.125 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5@eastus2.toml b/providers/requesty/models/azure/gpt-5@eastus2.toml new file mode 100644 index 00000000000..60c1714a76a --- /dev/null +++ b/providers/requesty/models/azure/gpt-5@eastus2.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.125 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5@francecentral.toml b/providers/requesty/models/azure/gpt-5@francecentral.toml new file mode 100644 index 00000000000..9d03bf44328 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5@francecentral.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.375 +output = 11 +cache_read = 0.1375 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5@swedencentral.toml b/providers/requesty/models/azure/gpt-5@swedencentral.toml new file mode 100644 index 00000000000..9d03bf44328 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5@swedencentral.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.375 +output = 11 +cache_read = 0.1375 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/gpt-5@uksouth.toml b/providers/requesty/models/azure/gpt-5@uksouth.toml new file mode 100644 index 00000000000..9d03bf44328 --- /dev/null +++ b/providers/requesty/models/azure/gpt-5@uksouth.toml @@ -0,0 +1,15 @@ +base_model = "openai/gpt-5" +base_model_omit = ["limit.input"] + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.375 +output = 11 +cache_read = 0.1375 + +[limit] +context = 200_000 +output = 100_000 diff --git a/providers/requesty/models/azure/o4-mini@eastus2.toml b/providers/requesty/models/azure/o4-mini@eastus2.toml new file mode 100644 index 00000000000..1456870e216 --- /dev/null +++ b/providers/requesty/models/azure/o4-mini@eastus2.toml @@ -0,0 +1,10 @@ +base_model = "openai/o4-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 4.4 +cache_read = 0.275 diff --git a/providers/requesty/models/azure/o4-mini@francecentral.toml b/providers/requesty/models/azure/o4-mini@francecentral.toml new file mode 100644 index 00000000000..80677831f10 --- /dev/null +++ b/providers/requesty/models/azure/o4-mini@francecentral.toml @@ -0,0 +1,10 @@ +base_model = "openai/o4-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.21 +output = 4.84 +cache_read = 0.3025 diff --git a/providers/requesty/models/azure/o4-mini@swedencentral.toml b/providers/requesty/models/azure/o4-mini@swedencentral.toml new file mode 100644 index 00000000000..80677831f10 --- /dev/null +++ b/providers/requesty/models/azure/o4-mini@swedencentral.toml @@ -0,0 +1,10 @@ +base_model = "openai/o4-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.21 +output = 4.84 +cache_read = 0.3025 diff --git a/providers/requesty/models/azure/o4-mini@westus3.toml b/providers/requesty/models/azure/o4-mini@westus3.toml new file mode 100644 index 00000000000..1456870e216 --- /dev/null +++ b/providers/requesty/models/azure/o4-mini@westus3.toml @@ -0,0 +1,10 @@ +base_model = "openai/o4-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 4.4 +cache_read = 0.275 diff --git a/providers/requesty/models/azure/openai-responses/gpt-4.1-mini@eastus2.toml b/providers/requesty/models/azure/openai-responses/gpt-4.1-mini@eastus2.toml new file mode 100644 index 00000000000..b2d9217542d --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-4.1-mini@eastus2.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1-mini" + +[cost] +input = 0.4 +output = 1.6 +cache_read = 0.1 diff --git a/providers/requesty/models/azure/openai-responses/gpt-4.1-mini@francecentral.toml b/providers/requesty/models/azure/openai-responses/gpt-4.1-mini@francecentral.toml new file mode 100644 index 00000000000..42eba8b8f9c --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-4.1-mini@francecentral.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1-mini" + +[cost] +input = 0.44 +output = 1.76 +cache_read = 0.11 diff --git a/providers/requesty/models/azure/openai-responses/gpt-4.1-mini@westus3.toml b/providers/requesty/models/azure/openai-responses/gpt-4.1-mini@westus3.toml new file mode 100644 index 00000000000..b2d9217542d --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-4.1-mini@westus3.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1-mini" + +[cost] +input = 0.4 +output = 1.6 +cache_read = 0.1 diff --git a/providers/requesty/models/azure/openai-responses/gpt-4.1-nano.toml b/providers/requesty/models/azure/openai-responses/gpt-4.1-nano.toml new file mode 100644 index 00000000000..f85c0947701 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-4.1-nano.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1-nano" + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.025 diff --git a/providers/requesty/models/azure/openai-responses/gpt-4.1-nano@eastus2.toml b/providers/requesty/models/azure/openai-responses/gpt-4.1-nano@eastus2.toml new file mode 100644 index 00000000000..f85c0947701 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-4.1-nano@eastus2.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1-nano" + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.025 diff --git a/providers/requesty/models/azure/openai-responses/gpt-4.1-nano@francecentral.toml b/providers/requesty/models/azure/openai-responses/gpt-4.1-nano@francecentral.toml new file mode 100644 index 00000000000..fe76c508a49 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-4.1-nano@francecentral.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1-nano" + +[cost] +input = 0.11 +output = 0.44 +cache_read = 0.0275 diff --git a/providers/requesty/models/azure/openai-responses/gpt-4.1-nano@swedencentral.toml b/providers/requesty/models/azure/openai-responses/gpt-4.1-nano@swedencentral.toml new file mode 100644 index 00000000000..fe76c508a49 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-4.1-nano@swedencentral.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1-nano" + +[cost] +input = 0.11 +output = 0.44 +cache_read = 0.0275 diff --git a/providers/requesty/models/azure/openai-responses/gpt-4.1-nano@westus3.toml b/providers/requesty/models/azure/openai-responses/gpt-4.1-nano@westus3.toml new file mode 100644 index 00000000000..f85c0947701 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-4.1-nano@westus3.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1-nano" + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.025 diff --git a/providers/requesty/models/azure/openai-responses/gpt-4.1.toml b/providers/requesty/models/azure/openai-responses/gpt-4.1.toml new file mode 100644 index 00000000000..1fdb518f628 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-4.1.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1" + +[cost] +input = 2 +output = 8 +cache_read = 0.5 diff --git a/providers/requesty/models/azure/openai-responses/gpt-4.1@eastus2.toml b/providers/requesty/models/azure/openai-responses/gpt-4.1@eastus2.toml new file mode 100644 index 00000000000..1fdb518f628 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-4.1@eastus2.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1" + +[cost] +input = 2 +output = 8 +cache_read = 0.5 diff --git a/providers/requesty/models/azure/openai-responses/gpt-4.1@francecentral.toml b/providers/requesty/models/azure/openai-responses/gpt-4.1@francecentral.toml new file mode 100644 index 00000000000..7ee4f7b59ac --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-4.1@francecentral.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1" + +[cost] +input = 2.2 +output = 8.8 +cache_read = 0.55 diff --git a/providers/requesty/models/azure/openai-responses/gpt-4.1@swedencentral.toml b/providers/requesty/models/azure/openai-responses/gpt-4.1@swedencentral.toml new file mode 100644 index 00000000000..7ee4f7b59ac --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-4.1@swedencentral.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1" + +[cost] +input = 2.2 +output = 8.8 +cache_read = 0.55 diff --git a/providers/requesty/models/azure/openai-responses/gpt-4.1@westus3.toml b/providers/requesty/models/azure/openai-responses/gpt-4.1@westus3.toml new file mode 100644 index 00000000000..1fdb518f628 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-4.1@westus3.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1" + +[cost] +input = 2 +output = 8 +cache_read = 0.5 diff --git a/providers/requesty/models/azure/openai-responses/gpt-5.4-pro@eastus2.toml b/providers/requesty/models/azure/openai-responses/gpt-5.4-pro@eastus2.toml new file mode 100644 index 00000000000..3505f167033 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-5.4-pro@eastus2.toml @@ -0,0 +1,11 @@ +base_model = "openai/gpt-5.4-pro" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 30 +output = 180 +cache_read = 30 diff --git a/providers/requesty/models/azure/openai-responses/gpt-5.4@eastus2.toml b/providers/requesty/models/azure/openai-responses/gpt-5.4@eastus2.toml new file mode 100644 index 00000000000..bceb46dba86 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-5.4@eastus2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.5 +output = 15 +cache_read = 0.25 diff --git a/providers/requesty/models/azure/openai-responses/gpt-5.4@francecentral.toml b/providers/requesty/models/azure/openai-responses/gpt-5.4@francecentral.toml new file mode 100644 index 00000000000..286deaff701 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-5.4@francecentral.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.75 +output = 16.5 +cache_read = 0.275 diff --git a/providers/requesty/models/azure/openai-responses/gpt-5.4@swedencentral.toml b/providers/requesty/models/azure/openai-responses/gpt-5.4@swedencentral.toml new file mode 100644 index 00000000000..286deaff701 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-5.4@swedencentral.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.75 +output = 16.5 +cache_read = 0.275 diff --git a/providers/requesty/models/azure/openai-responses/gpt-5.5@eastus2.toml b/providers/requesty/models/azure/openai-responses/gpt-5.5@eastus2.toml new file mode 100644 index 00000000000..b36d2d62074 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-5.5@eastus2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 30 +cache_read = 0.5 diff --git a/providers/requesty/models/azure/openai-responses/gpt-5.5@swedencentral.toml b/providers/requesty/models/azure/openai-responses/gpt-5.5@swedencentral.toml new file mode 100644 index 00000000000..b36d2d62074 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-5.5@swedencentral.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 30 +cache_read = 0.5 diff --git a/providers/requesty/models/azure/openai-responses/gpt-5.6-luna@eastus2.toml b/providers/requesty/models/azure/openai-responses/gpt-5.6-luna@eastus2.toml new file mode 100644 index 00000000000..08a1a8839f0 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-5.6-luna@eastus2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-luna" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1 +output = 6 +cache_read = 0.1 diff --git a/providers/requesty/models/azure/openai-responses/gpt-5.6-luna@swedencentral.toml b/providers/requesty/models/azure/openai-responses/gpt-5.6-luna@swedencentral.toml new file mode 100644 index 00000000000..5c3dc10ee84 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-5.6-luna@swedencentral.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-luna" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 6.6 +cache_read = 0.11 diff --git a/providers/requesty/models/azure/openai-responses/gpt-5.6-sol@eastus2.toml b/providers/requesty/models/azure/openai-responses/gpt-5.6-sol@eastus2.toml new file mode 100644 index 00000000000..edccc583108 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-5.6-sol@eastus2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-sol" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 30 +cache_read = 0.5 diff --git a/providers/requesty/models/azure/openai-responses/gpt-5.6-sol@swedencentral.toml b/providers/requesty/models/azure/openai-responses/gpt-5.6-sol@swedencentral.toml new file mode 100644 index 00000000000..dd1a19c3fb9 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-5.6-sol@swedencentral.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-sol" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 33 +cache_read = 0.55 diff --git a/providers/requesty/models/azure/openai-responses/gpt-5.6-terra@eastus2.toml b/providers/requesty/models/azure/openai-responses/gpt-5.6-terra@eastus2.toml new file mode 100644 index 00000000000..714e3afa796 --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-5.6-terra@eastus2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-terra" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.5 +output = 15 +cache_read = 0.25 diff --git a/providers/requesty/models/azure/openai-responses/gpt-5.6-terra@swedencentral.toml b/providers/requesty/models/azure/openai-responses/gpt-5.6-terra@swedencentral.toml new file mode 100644 index 00000000000..7dbc894119a --- /dev/null +++ b/providers/requesty/models/azure/openai-responses/gpt-5.6-terra@swedencentral.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-terra" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.75 +output = 16.5 +cache_read = 0.275 diff --git a/providers/requesty/models/bedrock/claude-fable-5@us-east-1.toml b/providers/requesty/models/bedrock/claude-fable-5@us-east-1.toml new file mode 100644 index 00000000000..68e17072888 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-fable-5@us-east-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-fable-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 11 +output = 55 +cache_read = 1.1 +cache_write = 13.75 diff --git a/providers/requesty/models/bedrock/claude-haiku-4-5.toml b/providers/requesty/models/bedrock/claude-haiku-4-5.toml new file mode 100644 index 00000000000..895510c3d47 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-haiku-4-5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-haiku-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1 +output = 5 +cache_read = 0.1 +cache_write = 1.25 diff --git a/providers/requesty/models/bedrock/claude-haiku-4-5@ap-northeast-1.toml b/providers/requesty/models/bedrock/claude-haiku-4-5@ap-northeast-1.toml new file mode 100644 index 00000000000..9569ab641f8 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-haiku-4-5@ap-northeast-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-haiku-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 5.5 +cache_read = 0.11 +cache_write = 1.375 diff --git a/providers/requesty/models/bedrock/claude-haiku-4-5@eu-central-1.toml b/providers/requesty/models/bedrock/claude-haiku-4-5@eu-central-1.toml new file mode 100644 index 00000000000..9569ab641f8 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-haiku-4-5@eu-central-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-haiku-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 5.5 +cache_read = 0.11 +cache_write = 1.375 diff --git a/providers/requesty/models/bedrock/claude-haiku-4-5@eu-north-1.toml b/providers/requesty/models/bedrock/claude-haiku-4-5@eu-north-1.toml new file mode 100644 index 00000000000..9569ab641f8 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-haiku-4-5@eu-north-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-haiku-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 5.5 +cache_read = 0.11 +cache_write = 1.375 diff --git a/providers/requesty/models/bedrock/claude-haiku-4-5@eu-west-1.toml b/providers/requesty/models/bedrock/claude-haiku-4-5@eu-west-1.toml new file mode 100644 index 00000000000..9569ab641f8 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-haiku-4-5@eu-west-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-haiku-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 5.5 +cache_read = 0.11 +cache_write = 1.375 diff --git a/providers/requesty/models/bedrock/claude-haiku-4-5@eu-west-3.toml b/providers/requesty/models/bedrock/claude-haiku-4-5@eu-west-3.toml new file mode 100644 index 00000000000..9569ab641f8 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-haiku-4-5@eu-west-3.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-haiku-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 5.5 +cache_read = 0.11 +cache_write = 1.375 diff --git a/providers/requesty/models/bedrock/claude-haiku-4-5@us-east-1.toml b/providers/requesty/models/bedrock/claude-haiku-4-5@us-east-1.toml new file mode 100644 index 00000000000..9569ab641f8 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-haiku-4-5@us-east-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-haiku-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 5.5 +cache_read = 0.11 +cache_write = 1.375 diff --git a/providers/requesty/models/bedrock/claude-haiku-4-5@us-east-2.toml b/providers/requesty/models/bedrock/claude-haiku-4-5@us-east-2.toml new file mode 100644 index 00000000000..9569ab641f8 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-haiku-4-5@us-east-2.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-haiku-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 5.5 +cache_read = 0.11 +cache_write = 1.375 diff --git a/providers/requesty/models/bedrock/claude-haiku-4-5@us-west-2.toml b/providers/requesty/models/bedrock/claude-haiku-4-5@us-west-2.toml new file mode 100644 index 00000000000..9569ab641f8 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-haiku-4-5@us-west-2.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-haiku-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 5.5 +cache_read = 0.11 +cache_write = 1.375 diff --git a/providers/requesty/models/bedrock/claude-opus-4-5.toml b/providers/requesty/models/bedrock/claude-opus-4-5.toml new file mode 100644 index 00000000000..9d8db2e267f --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 25 +cache_read = 0.5 +cache_write = 6.25 diff --git a/providers/requesty/models/bedrock/claude-opus-4-5@eu-central-1.toml b/providers/requesty/models/bedrock/claude-opus-4-5@eu-central-1.toml new file mode 100644 index 00000000000..38eabdfbecb --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-5@eu-central-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-4-5@eu-north-1.toml b/providers/requesty/models/bedrock/claude-opus-4-5@eu-north-1.toml new file mode 100644 index 00000000000..38eabdfbecb --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-5@eu-north-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-4-5@eu-west-1.toml b/providers/requesty/models/bedrock/claude-opus-4-5@eu-west-1.toml new file mode 100644 index 00000000000..38eabdfbecb --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-5@eu-west-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-4-5@eu-west-3.toml b/providers/requesty/models/bedrock/claude-opus-4-5@eu-west-3.toml new file mode 100644 index 00000000000..38eabdfbecb --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-5@eu-west-3.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-4-5@us-east-1.toml b/providers/requesty/models/bedrock/claude-opus-4-5@us-east-1.toml new file mode 100644 index 00000000000..38eabdfbecb --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-5@us-east-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-4-5@us-east-2.toml b/providers/requesty/models/bedrock/claude-opus-4-5@us-east-2.toml new file mode 100644 index 00000000000..38eabdfbecb --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-5@us-east-2.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-4-5@us-west-2.toml b/providers/requesty/models/bedrock/claude-opus-4-5@us-west-2.toml new file mode 100644 index 00000000000..38eabdfbecb --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-5@us-west-2.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-4-6.toml b/providers/requesty/models/bedrock/claude-opus-4-6.toml new file mode 100644 index 00000000000..4b8468b293d --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-6.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-6" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 25 +cache_read = 0.5 +cache_write = 6.25 diff --git a/providers/requesty/models/bedrock/claude-opus-4-7.toml b/providers/requesty/models/bedrock/claude-opus-4-7.toml new file mode 100644 index 00000000000..4edff5914b5 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-7.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-7" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 25 +cache_read = 0.5 +cache_write = 6.25 diff --git a/providers/requesty/models/bedrock/claude-opus-4-7@eu-central-1.toml b/providers/requesty/models/bedrock/claude-opus-4-7@eu-central-1.toml new file mode 100644 index 00000000000..1d51f34c674 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-7@eu-central-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-7" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-4-7@eu-north-1.toml b/providers/requesty/models/bedrock/claude-opus-4-7@eu-north-1.toml new file mode 100644 index 00000000000..1d51f34c674 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-7@eu-north-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-7" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-4-7@eu-west-1.toml b/providers/requesty/models/bedrock/claude-opus-4-7@eu-west-1.toml new file mode 100644 index 00000000000..1d51f34c674 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-7@eu-west-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-7" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-4-7@eu-west-3.toml b/providers/requesty/models/bedrock/claude-opus-4-7@eu-west-3.toml new file mode 100644 index 00000000000..1d51f34c674 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-7@eu-west-3.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-7" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-4-8.toml b/providers/requesty/models/bedrock/claude-opus-4-8.toml new file mode 100644 index 00000000000..d5cf84bf456 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-8.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-8" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 25 +cache_read = 0.5 +cache_write = 6.25 diff --git a/providers/requesty/models/bedrock/claude-opus-4-8@ap-northeast-1.toml b/providers/requesty/models/bedrock/claude-opus-4-8@ap-northeast-1.toml new file mode 100644 index 00000000000..40c63930a63 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-8@ap-northeast-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-8" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-4-8@eu-central-1.toml b/providers/requesty/models/bedrock/claude-opus-4-8@eu-central-1.toml new file mode 100644 index 00000000000..40c63930a63 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-8@eu-central-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-8" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-4-8@eu-north-1.toml b/providers/requesty/models/bedrock/claude-opus-4-8@eu-north-1.toml new file mode 100644 index 00000000000..40c63930a63 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-8@eu-north-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-8" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-4-8@eu-west-1.toml b/providers/requesty/models/bedrock/claude-opus-4-8@eu-west-1.toml new file mode 100644 index 00000000000..40c63930a63 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-8@eu-west-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-8" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-4-8@eu-west-3.toml b/providers/requesty/models/bedrock/claude-opus-4-8@eu-west-3.toml new file mode 100644 index 00000000000..40c63930a63 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-4-8@eu-west-3.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-8" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-5.toml b/providers/requesty/models/bedrock/claude-opus-5.toml new file mode 100644 index 00000000000..143e01133a7 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 25 +cache_read = 0.5 +cache_write = 6.25 diff --git a/providers/requesty/models/bedrock/claude-opus-5@ap-northeast-1.toml b/providers/requesty/models/bedrock/claude-opus-5@ap-northeast-1.toml new file mode 100644 index 00000000000..25840a265af --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-5@ap-northeast-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-5@eu-central-1.toml b/providers/requesty/models/bedrock/claude-opus-5@eu-central-1.toml new file mode 100644 index 00000000000..25840a265af --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-5@eu-central-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-5@eu-north-1.toml b/providers/requesty/models/bedrock/claude-opus-5@eu-north-1.toml new file mode 100644 index 00000000000..25840a265af --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-5@eu-north-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-5@eu-west-1.toml b/providers/requesty/models/bedrock/claude-opus-5@eu-west-1.toml new file mode 100644 index 00000000000..25840a265af --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-5@eu-west-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-opus-5@eu-west-3.toml b/providers/requesty/models/bedrock/claude-opus-5@eu-west-3.toml new file mode 100644 index 00000000000..25840a265af --- /dev/null +++ b/providers/requesty/models/bedrock/claude-opus-5@eu-west-3.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-5.toml b/providers/requesty/models/bedrock/claude-sonnet-4-5.toml new file mode 100644 index 00000000000..d0c775ffe7e --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3 +output = 15 +cache_read = 0.3 +cache_write = 3.75 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-5@eu-central-1.toml b/providers/requesty/models/bedrock/claude-sonnet-4-5@eu-central-1.toml new file mode 100644 index 00000000000..c69b1080b59 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-5@eu-central-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.3 +cache_write = 4.125 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-5@eu-north-1.toml b/providers/requesty/models/bedrock/claude-sonnet-4-5@eu-north-1.toml new file mode 100644 index 00000000000..c69b1080b59 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-5@eu-north-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.3 +cache_write = 4.125 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-5@eu-west-1.toml b/providers/requesty/models/bedrock/claude-sonnet-4-5@eu-west-1.toml new file mode 100644 index 00000000000..c69b1080b59 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-5@eu-west-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.3 +cache_write = 4.125 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-5@eu-west-3.toml b/providers/requesty/models/bedrock/claude-sonnet-4-5@eu-west-3.toml new file mode 100644 index 00000000000..c69b1080b59 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-5@eu-west-3.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.3 +cache_write = 4.125 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-5@us-east-1.toml b/providers/requesty/models/bedrock/claude-sonnet-4-5@us-east-1.toml new file mode 100644 index 00000000000..c69b1080b59 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-5@us-east-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.3 +cache_write = 4.125 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-5@us-east-2.toml b/providers/requesty/models/bedrock/claude-sonnet-4-5@us-east-2.toml new file mode 100644 index 00000000000..c69b1080b59 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-5@us-east-2.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.3 +cache_write = 4.125 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-5@us-west-2.toml b/providers/requesty/models/bedrock/claude-sonnet-4-5@us-west-2.toml new file mode 100644 index 00000000000..c69b1080b59 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-5@us-west-2.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.3 +cache_write = 4.125 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-6.toml b/providers/requesty/models/bedrock/claude-sonnet-4-6.toml new file mode 100644 index 00000000000..8aa9a27ca51 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-6.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-6" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3 +output = 15 +cache_read = 0.3 +cache_write = 3.75 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-6@ap-northeast-1.toml b/providers/requesty/models/bedrock/claude-sonnet-4-6@ap-northeast-1.toml new file mode 100644 index 00000000000..eec2d41d8b1 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-6@ap-northeast-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-6" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.3 +cache_write = 4.125 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-6@eu-central-1.toml b/providers/requesty/models/bedrock/claude-sonnet-4-6@eu-central-1.toml new file mode 100644 index 00000000000..eec2d41d8b1 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-6@eu-central-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-6" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.3 +cache_write = 4.125 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-6@eu-north-1.toml b/providers/requesty/models/bedrock/claude-sonnet-4-6@eu-north-1.toml new file mode 100644 index 00000000000..eec2d41d8b1 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-6@eu-north-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-6" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.3 +cache_write = 4.125 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-6@eu-west-1.toml b/providers/requesty/models/bedrock/claude-sonnet-4-6@eu-west-1.toml new file mode 100644 index 00000000000..eec2d41d8b1 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-6@eu-west-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-6" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.3 +cache_write = 4.125 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-6@eu-west-3.toml b/providers/requesty/models/bedrock/claude-sonnet-4-6@eu-west-3.toml new file mode 100644 index 00000000000..eec2d41d8b1 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-6@eu-west-3.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-6" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.3 +cache_write = 4.125 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-6@us-east-1.toml b/providers/requesty/models/bedrock/claude-sonnet-4-6@us-east-1.toml new file mode 100644 index 00000000000..eec2d41d8b1 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-6@us-east-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-6" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.3 +cache_write = 4.125 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-6@us-east-2.toml b/providers/requesty/models/bedrock/claude-sonnet-4-6@us-east-2.toml new file mode 100644 index 00000000000..eec2d41d8b1 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-6@us-east-2.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-6" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.3 +cache_write = 4.125 diff --git a/providers/requesty/models/bedrock/claude-sonnet-4-6@us-west-2.toml b/providers/requesty/models/bedrock/claude-sonnet-4-6@us-west-2.toml new file mode 100644 index 00000000000..eec2d41d8b1 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-4-6@us-west-2.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-6" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.3 +cache_write = 4.125 diff --git a/providers/requesty/models/bedrock/claude-sonnet-5.toml b/providers/requesty/models/bedrock/claude-sonnet-5.toml new file mode 100644 index 00000000000..6f4bad93f23 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2 +output = 10 +cache_read = 0.2 +cache_write = 2.5 diff --git a/providers/requesty/models/bedrock/claude-sonnet-5@ap-southeast-2.toml b/providers/requesty/models/bedrock/claude-sonnet-5@ap-southeast-2.toml new file mode 100644 index 00000000000..8f0d6c7dca5 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-5@ap-southeast-2.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.2 +output = 11 +cache_read = 0.22 +cache_write = 2.75 diff --git a/providers/requesty/models/bedrock/claude-sonnet-5@eu-central-1.toml b/providers/requesty/models/bedrock/claude-sonnet-5@eu-central-1.toml new file mode 100644 index 00000000000..8f0d6c7dca5 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-5@eu-central-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.2 +output = 11 +cache_read = 0.22 +cache_write = 2.75 diff --git a/providers/requesty/models/bedrock/claude-sonnet-5@eu-north-1.toml b/providers/requesty/models/bedrock/claude-sonnet-5@eu-north-1.toml new file mode 100644 index 00000000000..8f0d6c7dca5 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-5@eu-north-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.2 +output = 11 +cache_read = 0.22 +cache_write = 2.75 diff --git a/providers/requesty/models/bedrock/claude-sonnet-5@eu-west-1.toml b/providers/requesty/models/bedrock/claude-sonnet-5@eu-west-1.toml new file mode 100644 index 00000000000..8f0d6c7dca5 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-5@eu-west-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.2 +output = 11 +cache_read = 0.22 +cache_write = 2.75 diff --git a/providers/requesty/models/bedrock/claude-sonnet-5@eu-west-2.toml b/providers/requesty/models/bedrock/claude-sonnet-5@eu-west-2.toml new file mode 100644 index 00000000000..8f0d6c7dca5 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-5@eu-west-2.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.2 +output = 11 +cache_read = 0.22 +cache_write = 2.75 diff --git a/providers/requesty/models/bedrock/claude-sonnet-5@us-east-1.toml b/providers/requesty/models/bedrock/claude-sonnet-5@us-east-1.toml new file mode 100644 index 00000000000..8f0d6c7dca5 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-5@us-east-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.2 +output = 11 +cache_read = 0.22 +cache_write = 2.75 diff --git a/providers/requesty/models/bedrock/claude-sonnet-5@us-east-2.toml b/providers/requesty/models/bedrock/claude-sonnet-5@us-east-2.toml new file mode 100644 index 00000000000..8f0d6c7dca5 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-5@us-east-2.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.2 +output = 11 +cache_read = 0.22 +cache_write = 2.75 diff --git a/providers/requesty/models/bedrock/claude-sonnet-5@us-west-2.toml b/providers/requesty/models/bedrock/claude-sonnet-5@us-west-2.toml new file mode 100644 index 00000000000..8f0d6c7dca5 --- /dev/null +++ b/providers/requesty/models/bedrock/claude-sonnet-5@us-west-2.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.2 +output = 11 +cache_read = 0.22 +cache_write = 2.75 diff --git a/providers/requesty/models/bedrock/gpt-5.4@us-east-1.toml b/providers/requesty/models/bedrock/gpt-5.4@us-east-1.toml new file mode 100644 index 00000000000..286deaff701 --- /dev/null +++ b/providers/requesty/models/bedrock/gpt-5.4@us-east-1.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.75 +output = 16.5 +cache_read = 0.275 diff --git a/providers/requesty/models/bedrock/gpt-5.4@us-east-2.toml b/providers/requesty/models/bedrock/gpt-5.4@us-east-2.toml new file mode 100644 index 00000000000..286deaff701 --- /dev/null +++ b/providers/requesty/models/bedrock/gpt-5.4@us-east-2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.75 +output = 16.5 +cache_read = 0.275 diff --git a/providers/requesty/models/bedrock/gpt-5.4@us-west-2.toml b/providers/requesty/models/bedrock/gpt-5.4@us-west-2.toml new file mode 100644 index 00000000000..286deaff701 --- /dev/null +++ b/providers/requesty/models/bedrock/gpt-5.4@us-west-2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.75 +output = 16.5 +cache_read = 0.275 diff --git a/providers/requesty/models/bedrock/gpt-5.5@us-east-1.toml b/providers/requesty/models/bedrock/gpt-5.5@us-east-1.toml new file mode 100644 index 00000000000..49b3f2f9baf --- /dev/null +++ b/providers/requesty/models/bedrock/gpt-5.5@us-east-1.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 33 +cache_read = 0.55 diff --git a/providers/requesty/models/bedrock/gpt-5.5@us-east-2.toml b/providers/requesty/models/bedrock/gpt-5.5@us-east-2.toml new file mode 100644 index 00000000000..49b3f2f9baf --- /dev/null +++ b/providers/requesty/models/bedrock/gpt-5.5@us-east-2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 33 +cache_read = 0.55 diff --git a/providers/requesty/models/bedrock/kimi-k2.5@eu-north-1.toml b/providers/requesty/models/bedrock/kimi-k2.5@eu-north-1.toml new file mode 100644 index 00000000000..3e587cd72e8 --- /dev/null +++ b/providers/requesty/models/bedrock/kimi-k2.5@eu-north-1.toml @@ -0,0 +1,15 @@ +base_model = "moonshotai/kimi-k2.5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.72 +output = 3.6 +cache_read = 0.72 +cache_write = 0.72 + +[limit] +context = 128_000 +output = 16_000 diff --git a/providers/requesty/models/bedrock/kimi-k2.5@eu-west-2.toml b/providers/requesty/models/bedrock/kimi-k2.5@eu-west-2.toml new file mode 100644 index 00000000000..3e587cd72e8 --- /dev/null +++ b/providers/requesty/models/bedrock/kimi-k2.5@eu-west-2.toml @@ -0,0 +1,15 @@ +base_model = "moonshotai/kimi-k2.5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.72 +output = 3.6 +cache_read = 0.72 +cache_write = 0.72 + +[limit] +context = 128_000 +output = 16_000 diff --git a/providers/requesty/models/bedrock/kimi-k2.5@us-east-1.toml b/providers/requesty/models/bedrock/kimi-k2.5@us-east-1.toml new file mode 100644 index 00000000000..85308602d83 --- /dev/null +++ b/providers/requesty/models/bedrock/kimi-k2.5@us-east-1.toml @@ -0,0 +1,13 @@ +base_model = "moonshotai/kimi-k2.5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.6 +output = 3 + +[limit] +context = 128_000 +output = 16_000 diff --git a/providers/requesty/models/bedrock/kimi-k2.5@us-east-2.toml b/providers/requesty/models/bedrock/kimi-k2.5@us-east-2.toml new file mode 100644 index 00000000000..85308602d83 --- /dev/null +++ b/providers/requesty/models/bedrock/kimi-k2.5@us-east-2.toml @@ -0,0 +1,13 @@ +base_model = "moonshotai/kimi-k2.5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.6 +output = 3 + +[limit] +context = 128_000 +output = 16_000 diff --git a/providers/requesty/models/bedrock/kimi-k2.5@us-west-2.toml b/providers/requesty/models/bedrock/kimi-k2.5@us-west-2.toml new file mode 100644 index 00000000000..85308602d83 --- /dev/null +++ b/providers/requesty/models/bedrock/kimi-k2.5@us-west-2.toml @@ -0,0 +1,13 @@ +base_model = "moonshotai/kimi-k2.5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.6 +output = 3 + +[limit] +context = 128_000 +output = 16_000 diff --git a/providers/requesty/models/bedrock/minimax-m2.5@eu-central-1.toml b/providers/requesty/models/bedrock/minimax-m2.5@eu-central-1.toml new file mode 100644 index 00000000000..0ea2ba6a97a --- /dev/null +++ b/providers/requesty/models/bedrock/minimax-m2.5@eu-central-1.toml @@ -0,0 +1,14 @@ +base_model = "minimax/MiniMax-M2.5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.36 +output = 1.44 + +[limit] +context = 128_000 +output = 16_000 diff --git a/providers/requesty/models/bedrock/minimax-m2.5@eu-north-1.toml b/providers/requesty/models/bedrock/minimax-m2.5@eu-north-1.toml new file mode 100644 index 00000000000..0ea2ba6a97a --- /dev/null +++ b/providers/requesty/models/bedrock/minimax-m2.5@eu-north-1.toml @@ -0,0 +1,14 @@ +base_model = "minimax/MiniMax-M2.5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.36 +output = 1.44 + +[limit] +context = 128_000 +output = 16_000 diff --git a/providers/requesty/models/bedrock/minimax-m2.5@eu-south-1.toml b/providers/requesty/models/bedrock/minimax-m2.5@eu-south-1.toml new file mode 100644 index 00000000000..0ea2ba6a97a --- /dev/null +++ b/providers/requesty/models/bedrock/minimax-m2.5@eu-south-1.toml @@ -0,0 +1,14 @@ +base_model = "minimax/MiniMax-M2.5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.36 +output = 1.44 + +[limit] +context = 128_000 +output = 16_000 diff --git a/providers/requesty/models/bedrock/minimax-m2.5@eu-west-1.toml b/providers/requesty/models/bedrock/minimax-m2.5@eu-west-1.toml new file mode 100644 index 00000000000..0ea2ba6a97a --- /dev/null +++ b/providers/requesty/models/bedrock/minimax-m2.5@eu-west-1.toml @@ -0,0 +1,14 @@ +base_model = "minimax/MiniMax-M2.5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.36 +output = 1.44 + +[limit] +context = 128_000 +output = 16_000 diff --git a/providers/requesty/models/bedrock/minimax-m2.5@us-east-1.toml b/providers/requesty/models/bedrock/minimax-m2.5@us-east-1.toml new file mode 100644 index 00000000000..dc91bc4e84c --- /dev/null +++ b/providers/requesty/models/bedrock/minimax-m2.5@us-east-1.toml @@ -0,0 +1,14 @@ +base_model = "minimax/MiniMax-M2.5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 1.2 + +[limit] +context = 128_000 +output = 16_000 diff --git a/providers/requesty/models/bedrock/minimax-m2.5@us-east-2.toml b/providers/requesty/models/bedrock/minimax-m2.5@us-east-2.toml new file mode 100644 index 00000000000..dc91bc4e84c --- /dev/null +++ b/providers/requesty/models/bedrock/minimax-m2.5@us-east-2.toml @@ -0,0 +1,14 @@ +base_model = "minimax/MiniMax-M2.5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 1.2 + +[limit] +context = 128_000 +output = 16_000 diff --git a/providers/requesty/models/bedrock/minimax-m2.5@us-west-2.toml b/providers/requesty/models/bedrock/minimax-m2.5@us-west-2.toml new file mode 100644 index 00000000000..dc91bc4e84c --- /dev/null +++ b/providers/requesty/models/bedrock/minimax-m2.5@us-west-2.toml @@ -0,0 +1,14 @@ +base_model = "minimax/MiniMax-M2.5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 1.2 + +[limit] +context = 128_000 +output = 16_000 diff --git a/providers/requesty/models/coding/gemini-2.5-flash.toml b/providers/requesty/models/coding/gemini-2.5-flash.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-flash.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-flash@europe-central2.toml b/providers/requesty/models/coding/gemini-2.5-flash@europe-central2.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-flash@europe-central2.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-flash@europe-north1.toml b/providers/requesty/models/coding/gemini-2.5-flash@europe-north1.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-flash@europe-north1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-flash@europe-west1.toml b/providers/requesty/models/coding/gemini-2.5-flash@europe-west1.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-flash@europe-west1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-flash@europe-west4.toml b/providers/requesty/models/coding/gemini-2.5-flash@europe-west4.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-flash@europe-west4.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-flash@europe-west8.toml b/providers/requesty/models/coding/gemini-2.5-flash@europe-west8.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-flash@europe-west8.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-flash@us-central1.toml b/providers/requesty/models/coding/gemini-2.5-flash@us-central1.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-flash@us-central1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-flash@us-east1.toml b/providers/requesty/models/coding/gemini-2.5-flash@us-east1.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-flash@us-east1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-flash@us-east5.toml b/providers/requesty/models/coding/gemini-2.5-flash@us-east5.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-flash@us-east5.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-flash@us-south1.toml b/providers/requesty/models/coding/gemini-2.5-flash@us-south1.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-flash@us-south1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-flash@us-west1.toml b/providers/requesty/models/coding/gemini-2.5-flash@us-west1.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-flash@us-west1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-pro.toml b/providers/requesty/models/coding/gemini-2.5-pro.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-pro.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-pro@europe-central2.toml b/providers/requesty/models/coding/gemini-2.5-pro@europe-central2.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-pro@europe-central2.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-pro@europe-north1.toml b/providers/requesty/models/coding/gemini-2.5-pro@europe-north1.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-pro@europe-north1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-pro@europe-west1.toml b/providers/requesty/models/coding/gemini-2.5-pro@europe-west1.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-pro@europe-west1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-pro@europe-west4.toml b/providers/requesty/models/coding/gemini-2.5-pro@europe-west4.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-pro@europe-west4.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-pro@europe-west8.toml b/providers/requesty/models/coding/gemini-2.5-pro@europe-west8.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-pro@europe-west8.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-pro@us-central1.toml b/providers/requesty/models/coding/gemini-2.5-pro@us-central1.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-pro@us-central1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-pro@us-east1.toml b/providers/requesty/models/coding/gemini-2.5-pro@us-east1.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-pro@us-east1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-pro@us-east5.toml b/providers/requesty/models/coding/gemini-2.5-pro@us-east5.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-pro@us-east5.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-pro@us-south1.toml b/providers/requesty/models/coding/gemini-2.5-pro@us-south1.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-pro@us-south1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/coding/gemini-2.5-pro@us-west1.toml b/providers/requesty/models/coding/gemini-2.5-pro@us-west1.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/coding/gemini-2.5-pro@us-west1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/deepinfra/Qwen/Qwen3-235B-A22B.toml b/providers/requesty/models/deepinfra/Qwen/Qwen3-235B-A22B.toml new file mode 100644 index 00000000000..8e8e13c5304 --- /dev/null +++ b/providers/requesty/models/deepinfra/Qwen/Qwen3-235B-A22B.toml @@ -0,0 +1,15 @@ +base_model = "alibaba/qwen3-235b-a22b" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.2 +output = 0.6 +cache_read = 0.2 + +[limit] +context = 40_960 +output = 4_096 diff --git a/providers/requesty/models/deepinfra/Qwen/Qwen3-32B.toml b/providers/requesty/models/deepinfra/Qwen/Qwen3-32B.toml new file mode 100644 index 00000000000..479d6b28da1 --- /dev/null +++ b/providers/requesty/models/deepinfra/Qwen/Qwen3-32B.toml @@ -0,0 +1,14 @@ +base_model = "alibaba/qwen3-32b" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.3 +cache_read = 0.1 + +[limit] +context = 40_960 diff --git a/providers/requesty/models/deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct.toml b/providers/requesty/models/deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct.toml new file mode 100644 index 00000000000..8d43bd176f4 --- /dev/null +++ b/providers/requesty/models/deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct.toml @@ -0,0 +1,7 @@ +base_model = "alibaba/qwen3-coder-480b-a35b-instruct" +structured_output = true + +[cost] +input = 0.4 +output = 1.6 +cache_read = 0.4 diff --git a/providers/requesty/models/deepinfra/Qwen/Qwen3-Max.toml b/providers/requesty/models/deepinfra/Qwen/Qwen3-Max.toml new file mode 100644 index 00000000000..7eb845d2074 --- /dev/null +++ b/providers/requesty/models/deepinfra/Qwen/Qwen3-Max.toml @@ -0,0 +1,10 @@ +base_model = "alibaba/qwen3-max" +structured_output = false + +[cost] +input = 1.2 +output = 6 +cache_read = 0.24 + +[limit] +context = 256_000 diff --git a/providers/requesty/models/deepinfra/Qwen/Qwen3.5-27B.toml b/providers/requesty/models/deepinfra/Qwen/Qwen3.5-27B.toml new file mode 100644 index 00000000000..08f007deb8a --- /dev/null +++ b/providers/requesty/models/deepinfra/Qwen/Qwen3.5-27B.toml @@ -0,0 +1,9 @@ +base_model = "alibaba/qwen3.5-27b" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.26 +output = 2.6 diff --git a/providers/requesty/models/deepinfra/Qwen/Qwen3.5-35B-A3B.toml b/providers/requesty/models/deepinfra/Qwen/Qwen3.5-35B-A3B.toml new file mode 100644 index 00000000000..1b999d89798 --- /dev/null +++ b/providers/requesty/models/deepinfra/Qwen/Qwen3.5-35B-A3B.toml @@ -0,0 +1,10 @@ +base_model = "alibaba/qwen3.5-35b-a3b" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.14 +output = 1 +cache_read = 0.05 diff --git a/providers/requesty/models/deepinfra/Qwen/Qwen3.5-397B-A17B.toml b/providers/requesty/models/deepinfra/Qwen/Qwen3.5-397B-A17B.toml new file mode 100644 index 00000000000..e5a5b79e3cc --- /dev/null +++ b/providers/requesty/models/deepinfra/Qwen/Qwen3.5-397B-A17B.toml @@ -0,0 +1,10 @@ +base_model = "alibaba/qwen3.5-397b-a17b" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.49 +output = 3.6 +cache_read = 0.3 diff --git a/providers/requesty/models/deepinfra/XiaomiMiMo/MiMo-V2.5-Pro.toml b/providers/requesty/models/deepinfra/XiaomiMiMo/MiMo-V2.5-Pro.toml new file mode 100644 index 00000000000..fa9dc140a4c --- /dev/null +++ b/providers/requesty/models/deepinfra/XiaomiMiMo/MiMo-V2.5-Pro.toml @@ -0,0 +1,11 @@ +base_model = "xiaomi/mimo-v2.5-pro" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1 +output = 3 +cache_read = 0.2 diff --git a/providers/requesty/models/deepinfra/XiaomiMiMo/MiMo-V2.5.toml b/providers/requesty/models/deepinfra/XiaomiMiMo/MiMo-V2.5.toml new file mode 100644 index 00000000000..2e609483178 --- /dev/null +++ b/providers/requesty/models/deepinfra/XiaomiMiMo/MiMo-V2.5.toml @@ -0,0 +1,14 @@ +base_model = "xiaomi/mimo-v2.5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.4 +output = 2 +cache_read = 0.08 + +[limit] +context = 262_144 diff --git a/providers/requesty/models/deepinfra/deepseek-ai/DeepSeek-R1.toml b/providers/requesty/models/deepinfra/deepseek-ai/DeepSeek-R1.toml new file mode 100644 index 00000000000..8d89d82920c --- /dev/null +++ b/providers/requesty/models/deepinfra/deepseek-ai/DeepSeek-R1.toml @@ -0,0 +1,15 @@ +base_model = "deepseek/deepseek-r1" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.85 +output = 2.5 +cache_read = 0.85 + +[limit] +context = 64_000 +output = 8_192 diff --git a/providers/requesty/models/deepinfra/deepseek-ai/DeepSeek-V4-Flash.toml b/providers/requesty/models/deepinfra/deepseek-ai/DeepSeek-V4-Flash.toml new file mode 100644 index 00000000000..e2c31ceaa6c --- /dev/null +++ b/providers/requesty/models/deepinfra/deepseek-ai/DeepSeek-V4-Flash.toml @@ -0,0 +1,13 @@ +base_model = "deepseek/deepseek-v4-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.2 +cache_read = 0.02 + +[limit] +context = 1_048_576 diff --git a/providers/requesty/models/deepinfra/deepseek-ai/DeepSeek-V4-Pro.toml b/providers/requesty/models/deepinfra/deepseek-ai/DeepSeek-V4-Pro.toml new file mode 100644 index 00000000000..b0c7115c6af --- /dev/null +++ b/providers/requesty/models/deepinfra/deepseek-ai/DeepSeek-V4-Pro.toml @@ -0,0 +1,13 @@ +base_model = "deepseek/deepseek-v4-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.3 +output = 2.6 +cache_read = 0.1 + +[limit] +context = 1_048_576 diff --git a/providers/requesty/models/deepinfra/google/gemma-4-26B-A4B-it.toml b/providers/requesty/models/deepinfra/google/gemma-4-26B-A4B-it.toml new file mode 100644 index 00000000000..0307e36e53d --- /dev/null +++ b/providers/requesty/models/deepinfra/google/gemma-4-26B-A4B-it.toml @@ -0,0 +1,10 @@ +base_model = "google/gemma-4-26b-a4b-it" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.07 +output = 0.34 +cache_read = 0.07 diff --git a/providers/requesty/models/deepinfra/google/gemma-4-31B-it.toml b/providers/requesty/models/deepinfra/google/gemma-4-31B-it.toml new file mode 100644 index 00000000000..0734c341627 --- /dev/null +++ b/providers/requesty/models/deepinfra/google/gemma-4-31B-it.toml @@ -0,0 +1,9 @@ +base_model = "google/gemma-4-31b-it" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.13 +output = 0.38 diff --git a/providers/requesty/models/deepinfra/meta-llama/Llama-3.3-70B-Instruct.toml b/providers/requesty/models/deepinfra/meta-llama/Llama-3.3-70B-Instruct.toml new file mode 100644 index 00000000000..0dcdac2ecd8 --- /dev/null +++ b/providers/requesty/models/deepinfra/meta-llama/Llama-3.3-70B-Instruct.toml @@ -0,0 +1,11 @@ +base_model = "meta/llama-3.3-70b-instruct" +attachment = false +structured_output = false + +[cost] +input = 0.23 +output = 0.4 +cache_read = 0.23 + +[limit] +context = 131_072 diff --git a/providers/requesty/models/deepinfra/moonshotai/Kimi-K2.6.toml b/providers/requesty/models/deepinfra/moonshotai/Kimi-K2.6.toml new file mode 100644 index 00000000000..c043968f479 --- /dev/null +++ b/providers/requesty/models/deepinfra/moonshotai/Kimi-K2.6.toml @@ -0,0 +1,10 @@ +base_model = "moonshotai/kimi-k2.6" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.75 +output = 3.5 +cache_read = 0.15 diff --git a/providers/requesty/models/deepinfra/nvidia/Nemotron-3-Nano-30B-A3B.toml b/providers/requesty/models/deepinfra/nvidia/Nemotron-3-Nano-30B-A3B.toml new file mode 100644 index 00000000000..ee4940b8eef --- /dev/null +++ b/providers/requesty/models/deepinfra/nvidia/Nemotron-3-Nano-30B-A3B.toml @@ -0,0 +1,10 @@ +base_model = "nvidia/nemotron-3-nano-30b-a3b" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.05 +output = 0.2 diff --git a/providers/requesty/models/deepinfra/zai-org/GLM-4.5-Air.toml b/providers/requesty/models/deepinfra/zai-org/GLM-4.5-Air.toml new file mode 100644 index 00000000000..c6830f2d0c1 --- /dev/null +++ b/providers/requesty/models/deepinfra/zai-org/GLM-4.5-Air.toml @@ -0,0 +1,14 @@ +base_model = "zhipuai/glm-4.5-air" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.2 +output = 1.1 +cache_read = 0.2 + +[limit] +output = 4_096 diff --git a/providers/requesty/models/deepinfra/zai-org/GLM-4.5.toml b/providers/requesty/models/deepinfra/zai-org/GLM-4.5.toml new file mode 100644 index 00000000000..d6cef62f52c --- /dev/null +++ b/providers/requesty/models/deepinfra/zai-org/GLM-4.5.toml @@ -0,0 +1,14 @@ +base_model = "zhipuai/glm-4.5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.6 +output = 2.2 +cache_read = 0.6 + +[limit] +output = 4_096 diff --git a/providers/requesty/models/deepinfra/zai-org/GLM-5.1.toml b/providers/requesty/models/deepinfra/zai-org/GLM-5.1.toml new file mode 100644 index 00000000000..3f046caa8a6 --- /dev/null +++ b/providers/requesty/models/deepinfra/zai-org/GLM-5.1.toml @@ -0,0 +1,13 @@ +base_model = "zhipuai/glm-5.1" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.05 +output = 3.5 +cache_read = 0.205 + +[limit] +context = 202_752 diff --git a/providers/requesty/models/deepseek/deepseek-chat.toml b/providers/requesty/models/deepseek/deepseek-chat.toml new file mode 100644 index 00000000000..0cbcba76f23 --- /dev/null +++ b/providers/requesty/models/deepseek/deepseek-chat.toml @@ -0,0 +1,8 @@ +base_model = "deepseek/deepseek-chat" +attachment = false +structured_output = false + +[cost] +input = 0.14 +output = 0.28 +cache_read = 0.028 diff --git a/providers/requesty/models/deepseek/deepseek-reasoner.toml b/providers/requesty/models/deepseek/deepseek-reasoner.toml new file mode 100644 index 00000000000..c3ba1aba3d4 --- /dev/null +++ b/providers/requesty/models/deepseek/deepseek-reasoner.toml @@ -0,0 +1,12 @@ +base_model = "deepseek/deepseek-reasoner" +attachment = false +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.14 +output = 0.28 +cache_read = 0.028 diff --git a/providers/requesty/models/deepseek/deepseek-v4-flash.toml b/providers/requesty/models/deepseek/deepseek-v4-flash.toml new file mode 100644 index 00000000000..f7e8f616f65 --- /dev/null +++ b/providers/requesty/models/deepseek/deepseek-v4-flash.toml @@ -0,0 +1,10 @@ +base_model = "deepseek/deepseek-v4-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.14 +output = 0.28 +cache_read = 0.0028 diff --git a/providers/requesty/models/deepseek/deepseek-v4-pro.toml b/providers/requesty/models/deepseek/deepseek-v4-pro.toml new file mode 100644 index 00000000000..453db37acd9 --- /dev/null +++ b/providers/requesty/models/deepseek/deepseek-v4-pro.toml @@ -0,0 +1,10 @@ +base_model = "deepseek/deepseek-v4-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.435 +output = 0.87 +cache_read = 0.0145 diff --git a/providers/requesty/models/doubleword/deepseek-v4-flash.toml b/providers/requesty/models/doubleword/deepseek-v4-flash.toml new file mode 100644 index 00000000000..be08721df8a --- /dev/null +++ b/providers/requesty/models/doubleword/deepseek-v4-flash.toml @@ -0,0 +1,13 @@ +base_model = "deepseek/deepseek-v4-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.14 +output = 0.28 + +[limit] +context = 1_048_576 +output = 131_072 diff --git a/providers/requesty/models/doubleword/deepseek-v4-flash:flex.toml b/providers/requesty/models/doubleword/deepseek-v4-flash:flex.toml new file mode 100644 index 00000000000..6e24f9d9667 --- /dev/null +++ b/providers/requesty/models/doubleword/deepseek-v4-flash:flex.toml @@ -0,0 +1,13 @@ +base_model = "deepseek/deepseek-v4-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.2 + +[limit] +context = 1_048_576 +output = 131_072 diff --git a/providers/requesty/models/doubleword/deepseek-v4-pro.toml b/providers/requesty/models/doubleword/deepseek-v4-pro.toml new file mode 100644 index 00000000000..d4cafa5e941 --- /dev/null +++ b/providers/requesty/models/doubleword/deepseek-v4-pro.toml @@ -0,0 +1,13 @@ +base_model = "deepseek/deepseek-v4-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.74 +output = 3.48 + +[limit] +context = 1_048_576 +output = 131_072 diff --git a/providers/requesty/models/doubleword/deepseek-v4-pro:flex.toml b/providers/requesty/models/doubleword/deepseek-v4-pro:flex.toml new file mode 100644 index 00000000000..59c42d5d251 --- /dev/null +++ b/providers/requesty/models/doubleword/deepseek-v4-pro:flex.toml @@ -0,0 +1,13 @@ +base_model = "deepseek/deepseek-v4-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.31 +output = 2.75 + +[limit] +context = 1_048_576 +output = 131_072 diff --git a/providers/requesty/models/doubleword/glm-5.2.toml b/providers/requesty/models/doubleword/glm-5.2.toml new file mode 100644 index 00000000000..48d68f815c1 --- /dev/null +++ b/providers/requesty/models/doubleword/glm-5.2.toml @@ -0,0 +1,12 @@ +base_model = "zhipuai/glm-5.2" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.4 +output = 4.4 + +[limit] +context = 1_048_576 diff --git a/providers/requesty/models/doubleword/glm-5.2:flex.toml b/providers/requesty/models/doubleword/glm-5.2:flex.toml new file mode 100644 index 00000000000..52e6d82d34f --- /dev/null +++ b/providers/requesty/models/doubleword/glm-5.2:flex.toml @@ -0,0 +1,12 @@ +base_model = "zhipuai/glm-5.2" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.05 +output = 3.3 + +[limit] +context = 1_048_576 diff --git a/providers/requesty/models/fireworks/deepseek-v4-flash.toml b/providers/requesty/models/fireworks/deepseek-v4-flash.toml new file mode 100644 index 00000000000..601a2a4a276 --- /dev/null +++ b/providers/requesty/models/fireworks/deepseek-v4-flash.toml @@ -0,0 +1,13 @@ +base_model = "deepseek/deepseek-v4-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.14 +output = 0.28 +cache_read = 0.03 + +[limit] +output = 131_072 diff --git a/providers/requesty/models/fireworks/deepseek-v4-pro.toml b/providers/requesty/models/fireworks/deepseek-v4-pro.toml new file mode 100644 index 00000000000..eb199aadbd1 --- /dev/null +++ b/providers/requesty/models/fireworks/deepseek-v4-pro.toml @@ -0,0 +1,13 @@ +base_model = "deepseek/deepseek-v4-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.74 +output = 3.48 +cache_read = 0.15 + +[limit] +output = 131_072 diff --git a/providers/requesty/models/fireworks/glm-5.1.toml b/providers/requesty/models/fireworks/glm-5.1.toml new file mode 100644 index 00000000000..edefd277c3c --- /dev/null +++ b/providers/requesty/models/fireworks/glm-5.1.toml @@ -0,0 +1,14 @@ +base_model = "zhipuai/glm-5.1" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.4 +output = 4.4 +cache_read = 0.26 + +[limit] +context = 202_000 +output = 25_344 diff --git a/providers/requesty/models/fireworks/glm-5.2.toml b/providers/requesty/models/fireworks/glm-5.2.toml new file mode 100644 index 00000000000..f9c5b4f946c --- /dev/null +++ b/providers/requesty/models/fireworks/glm-5.2.toml @@ -0,0 +1,10 @@ +base_model = "zhipuai/glm-5.2" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.4 +output = 4.4 +cache_read = 0.14 diff --git a/providers/requesty/models/fireworks/gpt-oss-120b.toml b/providers/requesty/models/fireworks/gpt-oss-120b.toml new file mode 100644 index 00000000000..f388da21ed2 --- /dev/null +++ b/providers/requesty/models/fireworks/gpt-oss-120b.toml @@ -0,0 +1,13 @@ +base_model = "openai/gpt-oss-120b" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.15 +output = 0.6 +cache_read = 0.015 + +[limit] +output = 65_536 diff --git a/providers/requesty/models/fireworks/gpt-oss-20b.toml b/providers/requesty/models/fireworks/gpt-oss-20b.toml new file mode 100644 index 00000000000..aaf1135cc7f --- /dev/null +++ b/providers/requesty/models/fireworks/gpt-oss-20b.toml @@ -0,0 +1,13 @@ +base_model = "openai/gpt-oss-20b" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.07 +output = 0.3 +cache_read = 0.035 + +[limit] +output = 65_536 diff --git a/providers/requesty/models/fireworks/kimi-k2.6.toml b/providers/requesty/models/fireworks/kimi-k2.6.toml new file mode 100644 index 00000000000..c677b25ee38 --- /dev/null +++ b/providers/requesty/models/fireworks/kimi-k2.6.toml @@ -0,0 +1,13 @@ +base_model = "moonshotai/kimi-k2.6" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.95 +output = 4 +cache_read = 0.16 + +[limit] +output = 32_768 diff --git a/providers/requesty/models/fireworks/kimi-k2.7-code.toml b/providers/requesty/models/fireworks/kimi-k2.7-code.toml new file mode 100644 index 00000000000..b3c6f1b7662 --- /dev/null +++ b/providers/requesty/models/fireworks/kimi-k2.7-code.toml @@ -0,0 +1,10 @@ +base_model = "moonshotai/kimi-k2.7-code" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.95 +output = 4 +cache_read = 0.19 diff --git a/providers/requesty/models/fireworks/kimi-k3.toml b/providers/requesty/models/fireworks/kimi-k3.toml new file mode 100644 index 00000000000..9c841242c1e --- /dev/null +++ b/providers/requesty/models/fireworks/kimi-k3.toml @@ -0,0 +1,13 @@ +base_model = "moonshotai/kimi-k3" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3 +output = 15 +cache_read = 0.3 + +[limit] +context = 1_000_000 diff --git a/providers/requesty/models/fireworks/minimax-m2.7.toml b/providers/requesty/models/fireworks/minimax-m2.7.toml new file mode 100644 index 00000000000..8071e33f5cc --- /dev/null +++ b/providers/requesty/models/fireworks/minimax-m2.7.toml @@ -0,0 +1,15 @@ +base_model = "minimax/MiniMax-M2.7" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 1.2 +cache_read = 0.06 + +[limit] +context = 196_608 +output = 24_576 diff --git a/providers/requesty/models/fireworks/minimax-m3.toml b/providers/requesty/models/fireworks/minimax-m3.toml new file mode 100644 index 00000000000..d41ef3dd26b --- /dev/null +++ b/providers/requesty/models/fireworks/minimax-m3.toml @@ -0,0 +1,14 @@ +base_model = "minimax/MiniMax-M3" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 1.2 +cache_read = 0.06 + +[limit] +output = 512_000 diff --git a/providers/requesty/models/fireworks/qwen3.7-plus.toml b/providers/requesty/models/fireworks/qwen3.7-plus.toml new file mode 100644 index 00000000000..a5435a940af --- /dev/null +++ b/providers/requesty/models/fireworks/qwen3.7-plus.toml @@ -0,0 +1,15 @@ +base_model = "alibaba/qwen3.7-plus" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.4 +output = 1.6 +cache_read = 0.08 + +[limit] +context = 262_144 +output = 262_144 diff --git a/providers/requesty/models/google/gemini-2.5-flash-lite.toml b/providers/requesty/models/google/gemini-2.5-flash-lite.toml new file mode 100644 index 00000000000..f6e1634f5ef --- /dev/null +++ b/providers/requesty/models/google/gemini-2.5-flash-lite.toml @@ -0,0 +1,13 @@ +base_model = "google/gemini-2.5-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.01 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/google/gemini-2.5-flash.toml b/providers/requesty/models/google/gemini-2.5-flash.toml index c341820f3ed..2f9d566e3d9 100644 --- a/providers/requesty/models/google/gemini-2.5-flash.toml +++ b/providers/requesty/models/google/gemini-2.5-flash.toml @@ -1,26 +1,14 @@ -name = "Gemini 2.5 Flash" +base_model = "google/gemini-2.5-flash" description = "Fast Gemini model balancing multimodal reasoning, tool use, and cost" -family = "gemini-flash" -release_date = "2025-06-17" -last_updated = "2025-06-17" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -knowledge = "2025-01" -tool_call = true -open_weights = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] [cost] -input = 0.30 -output = 2.50 +input = 0.3 +output = 2.5 cache_read = 0.075 -cache_write = 0.55 [limit] -context = 1_048_576 -output = 65_536 - -[modalities] -input = ["text", "image", "audio", "video", "pdf"] -output = ["text"] +output = 65_535 diff --git a/providers/requesty/models/google/gemini-2.5-pro.toml b/providers/requesty/models/google/gemini-2.5-pro.toml index 87bcb7dff5e..02865e28607 100644 --- a/providers/requesty/models/google/gemini-2.5-pro.toml +++ b/providers/requesty/models/google/gemini-2.5-pro.toml @@ -1,7 +1,9 @@ base_model = "google/gemini-2.5-pro" base_model_omit = ["structured_output"] -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] [cost] input = 1.25 @@ -14,3 +16,6 @@ tier = { type = "context", size = 200_000 } input = 2.5 output = 15 cache_read = 0.25 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/google/gemini-3-flash-preview.toml b/providers/requesty/models/google/gemini-3-flash-preview.toml index ca138cdb2a2..e7ee12dfd18 100644 --- a/providers/requesty/models/google/gemini-3-flash-preview.toml +++ b/providers/requesty/models/google/gemini-3-flash-preview.toml @@ -1,25 +1,14 @@ -name = "Gemini 3 Flash" +base_model = "google/gemini-3-flash-preview" description = "Fast Gemini model balancing multimodal reasoning, tool use, and cost" -release_date = "2025-12-17" -last_updated = "2025-12-17" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -knowledge = "2025-01" -tool_call = true -open_weights = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] [cost] input = 0.5 output = 3 cache_read = 0.05 -cache_write = 1 [limit] -context = 1_048_576 -output = 65_536 - -[modalities] -input = ["text", "image", "audio", "video", "pdf"] -output = ["text"] +output = 65_535 diff --git a/providers/requesty/models/google/gemini-3-pro-preview.toml b/providers/requesty/models/google/gemini-3-pro-preview.toml index 037e789bfc9..ad0a4a8c536 100644 --- a/providers/requesty/models/google/gemini-3-pro-preview.toml +++ b/providers/requesty/models/google/gemini-3-pro-preview.toml @@ -1,26 +1,15 @@ -name = "Gemini 3 Pro" +base_model = "google/gemini-3-pro-preview" description = "Advanced Gemini model for complex reasoning, coding, and multimodal analysis" -family = "gemini-pro" -release_date = "2025-11-18" -last_updated = "2025-11-18" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -knowledge = "2025-01" -tool_call = true -open_weights = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] [cost] -input = 2.00 -output = 12.00 +input = 2 +output = 12 cache_read = 0.2 -cache_write = 4.50 +cache_write = 4.5 [limit] -context = 1_048_576 -output = 65_536 - -[modalities] -input = ["text", "image", "audio", "video", "pdf"] -output = ["text"] +output = 65_535 diff --git a/providers/requesty/models/google/gemini-3.1-flash-image.toml b/providers/requesty/models/google/gemini-3.1-flash-image.toml new file mode 100644 index 00000000000..eac77d825ab --- /dev/null +++ b/providers/requesty/models/google/gemini-3.1-flash-image.toml @@ -0,0 +1,11 @@ +base_model = "google/gemini-3.1-flash-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.5 +output = 2 diff --git a/providers/requesty/models/google/gemini-3.1-flash-lite.toml b/providers/requesty/models/google/gemini-3.1-flash-lite.toml new file mode 100644 index 00000000000..07daa9f62dd --- /dev/null +++ b/providers/requesty/models/google/gemini-3.1-flash-lite.toml @@ -0,0 +1,13 @@ +base_model = "google/gemini-3.1-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.25 +output = 1.5 +cache_read = 0.025 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/google/gemini-3.1-pro-preview.toml b/providers/requesty/models/google/gemini-3.1-pro-preview.toml new file mode 100644 index 00000000000..a0e675e7dbc --- /dev/null +++ b/providers/requesty/models/google/gemini-3.1-pro-preview.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-3.1-pro-preview" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2 +output = 12 +cache_read = 0.2 +cache_write = 4.5 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/google/gemma-4-31b-it.toml b/providers/requesty/models/google/gemma-4-31b-it.toml new file mode 100644 index 00000000000..47cdbc254f0 --- /dev/null +++ b/providers/requesty/models/google/gemma-4-31b-it.toml @@ -0,0 +1,12 @@ +base_model = "google/gemma-4-31b-it" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0 +output = 0 + +[limit] +output = 8_192 diff --git a/providers/requesty/models/groq/openai/gpt-oss-120b.toml b/providers/requesty/models/groq/openai/gpt-oss-120b.toml new file mode 100644 index 00000000000..df3e2c89124 --- /dev/null +++ b/providers/requesty/models/groq/openai/gpt-oss-120b.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-oss-120b" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.15 +output = 0.75 +cache_read = 0.15 diff --git a/providers/requesty/models/groq/openai/gpt-oss-20b.toml b/providers/requesty/models/groq/openai/gpt-oss-20b.toml new file mode 100644 index 00000000000..899288ee276 --- /dev/null +++ b/providers/requesty/models/groq/openai/gpt-oss-20b.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-oss-20b" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.5 +cache_read = 0.1 diff --git a/providers/requesty/models/inceptron/glm-5.2.toml b/providers/requesty/models/inceptron/glm-5.2.toml new file mode 100644 index 00000000000..675da94b5c4 --- /dev/null +++ b/providers/requesty/models/inceptron/glm-5.2.toml @@ -0,0 +1,13 @@ +base_model = "zhipuai/glm-5.2" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.2 +output = 4.2 +cache_read = 0.26 + +[limit] +output = 1_000_000 diff --git a/providers/requesty/models/inceptron/kimi-k2.6.toml b/providers/requesty/models/inceptron/kimi-k2.6.toml new file mode 100644 index 00000000000..5f99bde9909 --- /dev/null +++ b/providers/requesty/models/inceptron/kimi-k2.6.toml @@ -0,0 +1,10 @@ +base_model = "moonshotai/kimi-k2.6" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.8 +output = 3.5 +cache_read = 0.2 diff --git a/providers/requesty/models/inceptron/kimi-k2.7-Code.toml b/providers/requesty/models/inceptron/kimi-k2.7-Code.toml new file mode 100644 index 00000000000..f2c0e6c3755 --- /dev/null +++ b/providers/requesty/models/inceptron/kimi-k2.7-Code.toml @@ -0,0 +1,14 @@ +base_model = "moonshotai/kimi-k2.7-code" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.75 +output = 3.5 +cache_read = 0.2 + +[limit] +context = 256_000 +output = 256_000 diff --git a/providers/requesty/models/inceptron/minimax-m2.5.toml b/providers/requesty/models/inceptron/minimax-m2.5.toml new file mode 100644 index 00000000000..3c5b1dc2517 --- /dev/null +++ b/providers/requesty/models/inceptron/minimax-m2.5.toml @@ -0,0 +1,15 @@ +base_model = "minimax/MiniMax-M2.5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.28 +output = 1.1 +cache_read = 0.03 + +[limit] +context = 196_608 +output = 196_608 diff --git a/providers/requesty/models/minimaxi/minimax-m2.5-highspeed.toml b/providers/requesty/models/minimaxi/minimax-m2.5-highspeed.toml new file mode 100644 index 00000000000..61ae7eaea82 --- /dev/null +++ b/providers/requesty/models/minimaxi/minimax-m2.5-highspeed.toml @@ -0,0 +1,16 @@ +base_model = "minimax/MiniMax-M2.5-highspeed" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.6 +output = 2.4 +cache_read = 0.06 +cache_write = 2.4 + +[limit] +context = 200_000 +output = 128_000 diff --git a/providers/requesty/models/minimaxi/minimax-m2.5.toml b/providers/requesty/models/minimaxi/minimax-m2.5.toml new file mode 100644 index 00000000000..92992b68e5a --- /dev/null +++ b/providers/requesty/models/minimaxi/minimax-m2.5.toml @@ -0,0 +1,16 @@ +base_model = "minimax/MiniMax-M2.5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 1.2 +cache_read = 0.06 +cache_write = 1.2 + +[limit] +context = 200_000 +output = 128_000 diff --git a/providers/requesty/models/minimaxi/minimax-m2.7-highspeed.toml b/providers/requesty/models/minimaxi/minimax-m2.7-highspeed.toml new file mode 100644 index 00000000000..e5f19de7eec --- /dev/null +++ b/providers/requesty/models/minimaxi/minimax-m2.7-highspeed.toml @@ -0,0 +1,16 @@ +base_model = "minimax/MiniMax-M2.7-highspeed" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.6 +output = 2.4 +cache_read = 0.06 +cache_write = 1.2 + +[limit] +context = 200_000 +output = 128_000 diff --git a/providers/requesty/models/minimaxi/minimax-m2.7.toml b/providers/requesty/models/minimaxi/minimax-m2.7.toml new file mode 100644 index 00000000000..76024e290c2 --- /dev/null +++ b/providers/requesty/models/minimaxi/minimax-m2.7.toml @@ -0,0 +1,16 @@ +base_model = "minimax/MiniMax-M2.7" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 1.2 +cache_read = 0.06 +cache_write = 1.2 + +[limit] +context = 200_000 +output = 128_000 diff --git a/providers/requesty/models/minimaxi/minimax-m2.toml b/providers/requesty/models/minimaxi/minimax-m2.toml new file mode 100644 index 00000000000..3bca2dc2ca8 --- /dev/null +++ b/providers/requesty/models/minimaxi/minimax-m2.toml @@ -0,0 +1,15 @@ +base_model = "minimax/MiniMax-M2" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 1.2 +cache_read = 0.3 +cache_write = 1.2 + +[limit] +context = 200_000 diff --git a/providers/requesty/models/minimaxi/minimax-m3.toml b/providers/requesty/models/minimaxi/minimax-m3.toml new file mode 100644 index 00000000000..fe6e0e37082 --- /dev/null +++ b/providers/requesty/models/minimaxi/minimax-m3.toml @@ -0,0 +1,14 @@ +base_model = "minimax/MiniMax-M3" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 1.2 +cache_read = 0.06 + +[limit] +context = 1_000_000 diff --git a/providers/requesty/models/mistral/codestral-latest.toml b/providers/requesty/models/mistral/codestral-latest.toml new file mode 100644 index 00000000000..ce7d75ccef3 --- /dev/null +++ b/providers/requesty/models/mistral/codestral-latest.toml @@ -0,0 +1,10 @@ +base_model = "mistral/codestral-latest" +structured_output = true + +[cost] +input = 0.33 +output = 0.99 +cache_read = 0.33 + +[limit] +context = 131_072 diff --git a/providers/requesty/models/mistral/mistral-large-latest.toml b/providers/requesty/models/mistral/mistral-large-latest.toml new file mode 100644 index 00000000000..59594c042e4 --- /dev/null +++ b/providers/requesty/models/mistral/mistral-large-latest.toml @@ -0,0 +1,10 @@ +base_model = "mistral/mistral-large-latest" +structured_output = true + +[cost] +input = 0.55 +output = 1.65 +cache_read = 0.55 + +[limit] +context = 131_072 diff --git a/providers/requesty/models/mistral/mistral-medium-latest.toml b/providers/requesty/models/mistral/mistral-medium-latest.toml new file mode 100644 index 00000000000..7bca3c8807a --- /dev/null +++ b/providers/requesty/models/mistral/mistral-medium-latest.toml @@ -0,0 +1,13 @@ +base_model = "mistral/mistral-medium-latest" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.44 +output = 2.2 +cache_read = 0.44 + +[limit] +context = 131_072 diff --git a/providers/requesty/models/mistral/mistral-small-2603.toml b/providers/requesty/models/mistral/mistral-small-2603.toml new file mode 100644 index 00000000000..1cec852cb63 --- /dev/null +++ b/providers/requesty/models/mistral/mistral-small-2603.toml @@ -0,0 +1,11 @@ +base_model = "mistral/mistral-small-2603" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.165 +output = 0.66 +cache_read = 0.165 diff --git a/providers/requesty/models/mistral/mistral-small-latest.toml b/providers/requesty/models/mistral/mistral-small-latest.toml new file mode 100644 index 00000000000..59d94864d82 --- /dev/null +++ b/providers/requesty/models/mistral/mistral-small-latest.toml @@ -0,0 +1,11 @@ +base_model = "mistral/mistral-small-latest" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.165 +output = 0.66 +cache_read = 0.165 diff --git a/providers/requesty/models/moonshot/kimi-k2.5.toml b/providers/requesty/models/moonshot/kimi-k2.5.toml new file mode 100644 index 00000000000..20e62bcf3fe --- /dev/null +++ b/providers/requesty/models/moonshot/kimi-k2.5.toml @@ -0,0 +1,10 @@ +base_model = "moonshotai/kimi-k2.5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.6 +output = 3 +cache_read = 0.1 diff --git a/providers/requesty/models/moonshot/kimi-k2.6.toml b/providers/requesty/models/moonshot/kimi-k2.6.toml new file mode 100644 index 00000000000..3d00995b771 --- /dev/null +++ b/providers/requesty/models/moonshot/kimi-k2.6.toml @@ -0,0 +1,10 @@ +base_model = "moonshotai/kimi-k2.6" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.95 +output = 4 +cache_read = 0.16 diff --git a/providers/requesty/models/moonshot/kimi-k2.7-code.toml b/providers/requesty/models/moonshot/kimi-k2.7-code.toml new file mode 100644 index 00000000000..b3c6f1b7662 --- /dev/null +++ b/providers/requesty/models/moonshot/kimi-k2.7-code.toml @@ -0,0 +1,10 @@ +base_model = "moonshotai/kimi-k2.7-code" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.95 +output = 4 +cache_read = 0.19 diff --git a/providers/requesty/models/moonshot/kimi-k3.toml b/providers/requesty/models/moonshot/kimi-k3.toml new file mode 100644 index 00000000000..17eda7c7626 --- /dev/null +++ b/providers/requesty/models/moonshot/kimi-k3.toml @@ -0,0 +1,14 @@ +base_model = "moonshotai/kimi-k3" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3 +output = 15 +cache_read = 0.3 +cache_write = 15 + +[limit] +output = 1_048_576 diff --git a/providers/requesty/models/nebius/deepseek-ai/deepseek-v4-pro.toml b/providers/requesty/models/nebius/deepseek-ai/deepseek-v4-pro.toml new file mode 100644 index 00000000000..8867d07f04c --- /dev/null +++ b/providers/requesty/models/nebius/deepseek-ai/deepseek-v4-pro.toml @@ -0,0 +1,14 @@ +base_model = "deepseek/deepseek-v4-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.75 +output = 3.5 +cache_read = 1.75 + +[limit] +context = 164_000 +output = 128_000 diff --git a/providers/requesty/models/nebius/glm-5.2.toml b/providers/requesty/models/nebius/glm-5.2.toml new file mode 100644 index 00000000000..43b91468eaf --- /dev/null +++ b/providers/requesty/models/nebius/glm-5.2.toml @@ -0,0 +1,9 @@ +base_model = "zhipuai/glm-5.2" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.4 +output = 4.4 diff --git a/providers/requesty/models/nebius/kimi-k3.toml b/providers/requesty/models/nebius/kimi-k3.toml new file mode 100644 index 00000000000..1fe7b075353 --- /dev/null +++ b/providers/requesty/models/nebius/kimi-k3.toml @@ -0,0 +1,9 @@ +base_model = "moonshotai/kimi-k3" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3 +output = 15 diff --git a/providers/requesty/models/nebius/meta-llama/Llama-3.3-70B-Instruct.toml b/providers/requesty/models/nebius/meta-llama/Llama-3.3-70B-Instruct.toml new file mode 100644 index 00000000000..4989e2f0a98 --- /dev/null +++ b/providers/requesty/models/nebius/meta-llama/Llama-3.3-70B-Instruct.toml @@ -0,0 +1,8 @@ +base_model = "meta/llama-3.3-70b-instruct" +attachment = false +structured_output = true + +[cost] +input = 0.13 +output = 0.4 +cache_read = 0.13 diff --git a/providers/requesty/models/nebius/minimaxi/minimax-m2.5.toml b/providers/requesty/models/nebius/minimaxi/minimax-m2.5.toml new file mode 100644 index 00000000000..7147cf5ac25 --- /dev/null +++ b/providers/requesty/models/nebius/minimaxi/minimax-m2.5.toml @@ -0,0 +1,14 @@ +base_model = "minimax/MiniMax-M2.5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 1.2 +cache_read = 0.3 + +[limit] +context = 128_000 diff --git a/providers/requesty/models/nebius/moonshotai/kimi-k2.6.toml b/providers/requesty/models/nebius/moonshotai/kimi-k2.6.toml new file mode 100644 index 00000000000..aca0a5caa52 --- /dev/null +++ b/providers/requesty/models/nebius/moonshotai/kimi-k2.6.toml @@ -0,0 +1,14 @@ +base_model = "moonshotai/kimi-k2.6" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.95 +output = 4 +cache_read = 0.95 + +[limit] +context = 256_000 +output = 128_000 diff --git a/providers/requesty/models/nebius/nvidia/nemotron-3-super-120b-a12b.toml b/providers/requesty/models/nebius/nvidia/nemotron-3-super-120b-a12b.toml new file mode 100644 index 00000000000..2699a570d22 --- /dev/null +++ b/providers/requesty/models/nebius/nvidia/nemotron-3-super-120b-a12b.toml @@ -0,0 +1,14 @@ +base_model = "nvidia/nemotron-3-super-120b-a12b" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 0.9 +cache_read = 0.3 + +[limit] +context = 128_000 diff --git a/providers/requesty/models/nebius/nvidia/nemotron-3-ultra-550b-a55b.toml b/providers/requesty/models/nebius/nvidia/nemotron-3-ultra-550b-a55b.toml new file mode 100644 index 00000000000..1b20e8ee763 --- /dev/null +++ b/providers/requesty/models/nebius/nvidia/nemotron-3-ultra-550b-a55b.toml @@ -0,0 +1,14 @@ +base_model = "nvidia/nemotron-3-ultra-550b-a55b" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1 +output = 3 +cache_read = 1 + +[limit] +context = 128_000 diff --git a/providers/requesty/models/nebius/openai/gpt-oss-120b.toml b/providers/requesty/models/nebius/openai/gpt-oss-120b.toml new file mode 100644 index 00000000000..be16372071d --- /dev/null +++ b/providers/requesty/models/nebius/openai/gpt-oss-120b.toml @@ -0,0 +1,14 @@ +base_model = "openai/gpt-oss-120b" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.15 +output = 0.6 +cache_read = 0.15 + +[limit] +context = 131_000 +output = 128_000 diff --git a/providers/requesty/models/nebius/qwen/qwen3-32b.toml b/providers/requesty/models/nebius/qwen/qwen3-32b.toml new file mode 100644 index 00000000000..99cbbecf24a --- /dev/null +++ b/providers/requesty/models/nebius/qwen/qwen3-32b.toml @@ -0,0 +1,14 @@ +base_model = "alibaba/qwen3-32b" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.3 +cache_read = 0.1 + +[limit] +context = 128_000 diff --git a/providers/requesty/models/nebius/qwen/qwen3-next-80b-a3b-thinking.toml b/providers/requesty/models/nebius/qwen/qwen3-next-80b-a3b-thinking.toml new file mode 100644 index 00000000000..d6d119df9c8 --- /dev/null +++ b/providers/requesty/models/nebius/qwen/qwen3-next-80b-a3b-thinking.toml @@ -0,0 +1,14 @@ +base_model = "alibaba/qwen3-next-80b-a3b-thinking" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.15 +output = 1.2 +cache_read = 0.15 + +[limit] +context = 128_000 diff --git a/providers/requesty/models/nebius/qwen/qwen3.5-397b-a17b.toml b/providers/requesty/models/nebius/qwen/qwen3.5-397b-a17b.toml new file mode 100644 index 00000000000..0595ecba4b3 --- /dev/null +++ b/providers/requesty/models/nebius/qwen/qwen3.5-397b-a17b.toml @@ -0,0 +1,13 @@ +base_model = "alibaba/qwen3.5-397b-a17b" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.6 +output = 3.6 +cache_read = 0.6 + +[limit] +context = 128_000 diff --git a/providers/requesty/models/nebius/zai-org/glm-5.1.toml b/providers/requesty/models/nebius/zai-org/glm-5.1.toml new file mode 100644 index 00000000000..e0c7cc98611 --- /dev/null +++ b/providers/requesty/models/nebius/zai-org/glm-5.1.toml @@ -0,0 +1,10 @@ +base_model = "zhipuai/glm-5.1" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.4 +output = 4.4 +cache_read = 1.4 diff --git a/providers/requesty/models/novita/GLM-5.toml b/providers/requesty/models/novita/GLM-5.toml new file mode 100644 index 00000000000..8805d66434d --- /dev/null +++ b/providers/requesty/models/novita/GLM-5.toml @@ -0,0 +1,14 @@ +base_model = "zhipuai/glm-5" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1 +output = 3.2 +cache_read = 0.2 + +[limit] +context = 202_800 diff --git a/providers/requesty/models/novita/deepseek/deepseek-r1.toml b/providers/requesty/models/novita/deepseek/deepseek-r1.toml new file mode 100644 index 00000000000..d94b037eeb8 --- /dev/null +++ b/providers/requesty/models/novita/deepseek/deepseek-r1.toml @@ -0,0 +1,14 @@ +base_model = "deepseek/deepseek-r1" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 4 +output = 4 +cache_read = 4 + +[limit] +context = 64_000 diff --git a/providers/requesty/models/novita/deepseek/deepseek-v4-flash.toml b/providers/requesty/models/novita/deepseek/deepseek-v4-flash.toml new file mode 100644 index 00000000000..8f1e97a43a3 --- /dev/null +++ b/providers/requesty/models/novita/deepseek/deepseek-v4-flash.toml @@ -0,0 +1,12 @@ +base_model = "deepseek/deepseek-v4-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.14 +output = 0.28 + +[limit] +context = 1_048_576 diff --git a/providers/requesty/models/novita/google/gemma-4-26b-a4b-it.toml b/providers/requesty/models/novita/google/gemma-4-26b-a4b-it.toml new file mode 100644 index 00000000000..45d7bc0ad6c --- /dev/null +++ b/providers/requesty/models/novita/google/gemma-4-26b-a4b-it.toml @@ -0,0 +1,13 @@ +base_model = "google/gemma-4-26b-a4b-it" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.13 +output = 0.4 +cache_read = 0.13 + +[limit] +output = 131_072 diff --git a/providers/requesty/models/novita/meta-llama/llama-3.3-70b-instruct.toml b/providers/requesty/models/novita/meta-llama/llama-3.3-70b-instruct.toml new file mode 100644 index 00000000000..8bfcfb06f65 --- /dev/null +++ b/providers/requesty/models/novita/meta-llama/llama-3.3-70b-instruct.toml @@ -0,0 +1,11 @@ +base_model = "meta/llama-3.3-70b-instruct" +attachment = false +structured_output = false + +[cost] +input = 0.39 +output = 0.39 +cache_read = 0.39 + +[limit] +context = 131_072 diff --git a/providers/requesty/models/novita/minimax/minimax-m2.7-highspeed.toml b/providers/requesty/models/novita/minimax/minimax-m2.7-highspeed.toml new file mode 100644 index 00000000000..3ace6887eea --- /dev/null +++ b/providers/requesty/models/novita/minimax/minimax-m2.7-highspeed.toml @@ -0,0 +1,10 @@ +base_model = "minimax/MiniMax-M2.7-highspeed" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.6 +output = 2.4 diff --git a/providers/requesty/models/novita/minimax/minimax-m2.7.toml b/providers/requesty/models/novita/minimax/minimax-m2.7.toml new file mode 100644 index 00000000000..ee72c2193da --- /dev/null +++ b/providers/requesty/models/novita/minimax/minimax-m2.7.toml @@ -0,0 +1,15 @@ +base_model = "minimax/MiniMax-M2.7" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 1.2 +cache_read = 0.06 + +[limit] +context = 200_000 +output = 128_000 diff --git a/providers/requesty/models/novita/mistralai/mistral-nemo.toml b/providers/requesty/models/novita/mistralai/mistral-nemo.toml new file mode 100644 index 00000000000..a6bafda1497 --- /dev/null +++ b/providers/requesty/models/novita/mistralai/mistral-nemo.toml @@ -0,0 +1,10 @@ +base_model = "mistral/mistral-nemo" +structured_output = false + +[cost] +input = 0.17 +output = 0.17 +cache_read = 0.17 + +[limit] +context = 131_072 diff --git a/providers/requesty/models/novita/qwen/qwen3.5-397b-a17b.toml b/providers/requesty/models/novita/qwen/qwen3.5-397b-a17b.toml new file mode 100644 index 00000000000..aa6e4922477 --- /dev/null +++ b/providers/requesty/models/novita/qwen/qwen3.5-397b-a17b.toml @@ -0,0 +1,10 @@ +base_model = "alibaba/qwen3.5-397b-a17b" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.6 +output = 3.6 +cache_read = 0.6 diff --git a/providers/requesty/models/novita/stepfun/step-3.7-flash.toml b/providers/requesty/models/novita/stepfun/step-3.7-flash.toml new file mode 100644 index 00000000000..d789c40c04d --- /dev/null +++ b/providers/requesty/models/novita/stepfun/step-3.7-flash.toml @@ -0,0 +1,15 @@ +base_model = "stepfun/step-3.7-flash" +base_model_omit = ["limit.input"] +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.2 +output = 1.15 +cache_read = 0.04 + +[limit] +context = 262_144 diff --git a/providers/requesty/models/novita/tencent/hy3.toml b/providers/requesty/models/novita/tencent/hy3.toml new file mode 100644 index 00000000000..b00734477c5 --- /dev/null +++ b/providers/requesty/models/novita/tencent/hy3.toml @@ -0,0 +1,15 @@ +base_model = "tencent/hy3" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.14 +output = 0.58 +cache_read = 0.035 + +[limit] +context = 262_144 +output = 262_144 diff --git a/providers/requesty/models/novita/zai-org/glm-4.6.toml b/providers/requesty/models/novita/zai-org/glm-4.6.toml new file mode 100644 index 00000000000..f6378781fec --- /dev/null +++ b/providers/requesty/models/novita/zai-org/glm-4.6.toml @@ -0,0 +1,11 @@ +base_model = "zhipuai/glm-4.6" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.6 +output = 2.2 +cache_read = 0.6 diff --git a/providers/requesty/models/novita/zai-org/glm-5.1.toml b/providers/requesty/models/novita/zai-org/glm-5.1.toml new file mode 100644 index 00000000000..07e4491c29e --- /dev/null +++ b/providers/requesty/models/novita/zai-org/glm-5.1.toml @@ -0,0 +1,12 @@ +base_model = "zhipuai/glm-5.1" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.38 +output = 4.4 + +[limit] +context = 204_800 diff --git a/providers/requesty/models/nvidia/nemotron-3-nano-30b-a3b.toml b/providers/requesty/models/nvidia/nemotron-3-nano-30b-a3b.toml new file mode 100644 index 00000000000..cd378e77803 --- /dev/null +++ b/providers/requesty/models/nvidia/nemotron-3-nano-30b-a3b.toml @@ -0,0 +1,10 @@ +base_model = "nvidia/nemotron-3-nano-30b-a3b" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0 +output = 0 diff --git a/providers/requesty/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning.toml b/providers/requesty/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning.toml new file mode 100644 index 00000000000..e1284c10a00 --- /dev/null +++ b/providers/requesty/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning.toml @@ -0,0 +1,14 @@ +base_model = "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0 +output = 0 + +[limit] +context = 131_072 +output = 20_480 diff --git a/providers/requesty/models/nvidia/nemotron-3-super-120b-a12b.toml b/providers/requesty/models/nvidia/nemotron-3-super-120b-a12b.toml new file mode 100644 index 00000000000..6f9885f1df3 --- /dev/null +++ b/providers/requesty/models/nvidia/nemotron-3-super-120b-a12b.toml @@ -0,0 +1,14 @@ +base_model = "nvidia/nemotron-3-super-120b-a12b" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0 +output = 0 + +[limit] +context = 1_048_576 +output = 65_536 diff --git a/providers/requesty/models/nvidia/nemotron-3-ultra-550b-a55b.toml b/providers/requesty/models/nvidia/nemotron-3-ultra-550b-a55b.toml new file mode 100644 index 00000000000..09cfc476850 --- /dev/null +++ b/providers/requesty/models/nvidia/nemotron-3-ultra-550b-a55b.toml @@ -0,0 +1,14 @@ +base_model = "nvidia/nemotron-3-ultra-550b-a55b" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0 +output = 0 + +[limit] +context = 1_048_576 +output = 65_536 diff --git a/providers/requesty/models/nvidia/nemotron-3.5-content-safety.toml b/providers/requesty/models/nvidia/nemotron-3.5-content-safety.toml new file mode 100644 index 00000000000..ad31313ecc8 --- /dev/null +++ b/providers/requesty/models/nvidia/nemotron-3.5-content-safety.toml @@ -0,0 +1,13 @@ +base_model = "nvidia/nemotron-3.5-content-safety" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0 +output = 0 + +[limit] +context = 131_072 diff --git a/providers/requesty/models/openai-responses/gpt-4.1-mini.toml b/providers/requesty/models/openai-responses/gpt-4.1-mini.toml new file mode 100644 index 00000000000..b2d9217542d --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-4.1-mini.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1-mini" + +[cost] +input = 0.4 +output = 1.6 +cache_read = 0.1 diff --git a/providers/requesty/models/openai-responses/gpt-4.1-nano.toml b/providers/requesty/models/openai-responses/gpt-4.1-nano.toml new file mode 100644 index 00000000000..f85c0947701 --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-4.1-nano.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1-nano" + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.025 diff --git a/providers/requesty/models/openai-responses/gpt-4.1.toml b/providers/requesty/models/openai-responses/gpt-4.1.toml new file mode 100644 index 00000000000..1fdb518f628 --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-4.1.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1" + +[cost] +input = 2 +output = 8 +cache_read = 0.5 diff --git a/providers/requesty/models/openai-responses/gpt-5-codex.toml b/providers/requesty/models/openai-responses/gpt-5-codex.toml new file mode 100644 index 00000000000..42a5f4633b0 --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5-codex.toml @@ -0,0 +1,11 @@ +base_model = "openai/gpt-5-codex" +attachment = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.125 diff --git a/providers/requesty/models/openai-responses/gpt-5-mini.toml b/providers/requesty/models/openai-responses/gpt-5-mini.toml new file mode 100644 index 00000000000..966842b119e --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5-mini.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.25 +output = 2 +cache_read = 0.025 diff --git a/providers/requesty/models/openai-responses/gpt-5-nano.toml b/providers/requesty/models/openai-responses/gpt-5-nano.toml new file mode 100644 index 00000000000..b7acce0a6cb --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5-nano.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5-nano" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.05 +output = 0.4 +cache_read = 0.005 diff --git a/providers/requesty/models/openai-responses/gpt-5-pro.toml b/providers/requesty/models/openai-responses/gpt-5-pro.toml new file mode 100644 index 00000000000..8b7f4e9908e --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5-pro.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 15 +output = 120 +cache_read = 15 diff --git a/providers/requesty/models/openai-responses/gpt-5.1-codex.toml b/providers/requesty/models/openai-responses/gpt-5.1-codex.toml new file mode 100644 index 00000000000..38c0584b666 --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5.1-codex.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.1-codex" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.125 diff --git a/providers/requesty/models/openai-responses/gpt-5.1.toml b/providers/requesty/models/openai-responses/gpt-5.1.toml new file mode 100644 index 00000000000..c74935fd8de --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5.1.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.1" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.125 diff --git a/providers/requesty/models/openai-responses/gpt-5.2-codex.toml b/providers/requesty/models/openai-responses/gpt-5.2-codex.toml new file mode 100644 index 00000000000..f86e1c0d4ae --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5.2-codex.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.2-codex" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.75 +output = 14 +cache_read = 0.175 diff --git a/providers/requesty/models/openai-responses/gpt-5.2.toml b/providers/requesty/models/openai-responses/gpt-5.2.toml new file mode 100644 index 00000000000..a3d9d17fb1f --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5.2.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.2" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.75 +output = 14 +cache_read = 0.175 diff --git a/providers/requesty/models/openai-responses/gpt-5.3-codex.toml b/providers/requesty/models/openai-responses/gpt-5.3-codex.toml new file mode 100644 index 00000000000..2cd5a8d5b71 --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5.3-codex.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.3-codex" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.75 +output = 14 +cache_read = 0.175 diff --git a/providers/requesty/models/openai-responses/gpt-5.4-mini.toml b/providers/requesty/models/openai-responses/gpt-5.4-mini.toml new file mode 100644 index 00000000000..be3542d6282 --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5.4-mini.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.75 +output = 4.5 +cache_read = 0.075 diff --git a/providers/requesty/models/openai-responses/gpt-5.4-nano.toml b/providers/requesty/models/openai-responses/gpt-5.4-nano.toml new file mode 100644 index 00000000000..223166b82f9 --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5.4-nano.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4-nano" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.2 +output = 1.25 +cache_read = 0.02 diff --git a/providers/requesty/models/openai-responses/gpt-5.4-pro.toml b/providers/requesty/models/openai-responses/gpt-5.4-pro.toml new file mode 100644 index 00000000000..3505f167033 --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5.4-pro.toml @@ -0,0 +1,11 @@ +base_model = "openai/gpt-5.4-pro" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 30 +output = 180 +cache_read = 30 diff --git a/providers/requesty/models/openai-responses/gpt-5.4.toml b/providers/requesty/models/openai-responses/gpt-5.4.toml new file mode 100644 index 00000000000..bceb46dba86 --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5.4.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.5 +output = 15 +cache_read = 0.25 diff --git a/providers/requesty/models/openai-responses/gpt-5.5-pro.toml b/providers/requesty/models/openai-responses/gpt-5.5-pro.toml new file mode 100644 index 00000000000..1e20700a584 --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5.5-pro.toml @@ -0,0 +1,9 @@ +base_model = "openai/gpt-5.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 30 +output = 180 diff --git a/providers/requesty/models/openai-responses/gpt-5.5.toml b/providers/requesty/models/openai-responses/gpt-5.5.toml new file mode 100644 index 00000000000..b36d2d62074 --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5.5.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 30 +cache_read = 0.5 diff --git a/providers/requesty/models/openai-responses/gpt-5.6-luna.toml b/providers/requesty/models/openai-responses/gpt-5.6-luna.toml new file mode 100644 index 00000000000..08a1a8839f0 --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5.6-luna.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-luna" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1 +output = 6 +cache_read = 0.1 diff --git a/providers/requesty/models/openai-responses/gpt-5.6-sol.toml b/providers/requesty/models/openai-responses/gpt-5.6-sol.toml new file mode 100644 index 00000000000..edccc583108 --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5.6-sol.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-sol" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 30 +cache_read = 0.5 diff --git a/providers/requesty/models/openai-responses/gpt-5.6-terra.toml b/providers/requesty/models/openai-responses/gpt-5.6-terra.toml new file mode 100644 index 00000000000..714e3afa796 --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5.6-terra.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-terra" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.5 +output = 15 +cache_read = 0.25 diff --git a/providers/requesty/models/openai-responses/gpt-5.toml b/providers/requesty/models/openai-responses/gpt-5.toml new file mode 100644 index 00000000000..e097ebcbdd9 --- /dev/null +++ b/providers/requesty/models/openai-responses/gpt-5.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.125 diff --git a/providers/requesty/models/openai-responses/o3-mini.toml b/providers/requesty/models/openai-responses/o3-mini.toml new file mode 100644 index 00000000000..858665dd751 --- /dev/null +++ b/providers/requesty/models/openai-responses/o3-mini.toml @@ -0,0 +1,10 @@ +base_model = "openai/o3-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 4.4 +cache_read = 0.55 diff --git a/providers/requesty/models/openai-responses/o3-pro.toml b/providers/requesty/models/openai-responses/o3-pro.toml new file mode 100644 index 00000000000..f73d6365bcd --- /dev/null +++ b/providers/requesty/models/openai-responses/o3-pro.toml @@ -0,0 +1,10 @@ +base_model = "openai/o3-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 20 +output = 80 +cache_read = 20 diff --git a/providers/requesty/models/openai-responses/o4-mini.toml b/providers/requesty/models/openai-responses/o4-mini.toml new file mode 100644 index 00000000000..1456870e216 --- /dev/null +++ b/providers/requesty/models/openai-responses/o4-mini.toml @@ -0,0 +1,10 @@ +base_model = "openai/o4-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 4.4 +cache_read = 0.275 diff --git a/providers/requesty/models/openai/gpt-4.1-mini.toml b/providers/requesty/models/openai/gpt-4.1-mini.toml index 5b1b2499bc4..e54e39ef528 100644 --- a/providers/requesty/models/openai/gpt-4.1-mini.toml +++ b/providers/requesty/models/openai/gpt-4.1-mini.toml @@ -1,24 +1,7 @@ -name = "GPT-4.1 Mini" +base_model = "openai/gpt-4.1-mini" description = "Compact GPT model for low-latency assistance and high-volume workloads" -family = "gpt-mini" -release_date = "2025-04-14" -last_updated = "2025-04-14" -attachment = true -reasoning = false -temperature = true -tool_call = true -knowledge = "2024-04" -open_weights = false [cost] -input = 0.40 -output = 1.60 -cache_read = 0.10 - -[limit] -context = 1_047_576 -output = 32_768 - -[modalities] -input = ["text", "image"] -output = ["text"] +input = 0.4 +output = 1.6 +cache_read = 0.1 diff --git a/providers/requesty/models/openai/gpt-4.1-nano.toml b/providers/requesty/models/openai/gpt-4.1-nano.toml new file mode 100644 index 00000000000..f85c0947701 --- /dev/null +++ b/providers/requesty/models/openai/gpt-4.1-nano.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4.1-nano" + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.025 diff --git a/providers/requesty/models/openai/gpt-4.1.toml b/providers/requesty/models/openai/gpt-4.1.toml index 67e617230aa..0501119e224 100644 --- a/providers/requesty/models/openai/gpt-4.1.toml +++ b/providers/requesty/models/openai/gpt-4.1.toml @@ -5,6 +5,3 @@ base_model_omit = ["structured_output"] input = 2 output = 8 cache_read = 0.5 - -[modalities] -input = ["text", "image"] diff --git a/providers/requesty/models/openai/gpt-4o-2024-05-13.toml b/providers/requesty/models/openai/gpt-4o-2024-05-13.toml new file mode 100644 index 00000000000..bbc63a9e61b --- /dev/null +++ b/providers/requesty/models/openai/gpt-4o-2024-05-13.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4o-2024-05-13" + +[cost] +input = 2.5 +output = 10 +cache_read = 2.5 diff --git a/providers/requesty/models/openai/gpt-4o-2024-08-06.toml b/providers/requesty/models/openai/gpt-4o-2024-08-06.toml new file mode 100644 index 00000000000..344cd161a70 --- /dev/null +++ b/providers/requesty/models/openai/gpt-4o-2024-08-06.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4o-2024-08-06" + +[cost] +input = 2.5 +output = 10 +cache_read = 1.25 diff --git a/providers/requesty/models/openai/gpt-4o-2024-11-20.toml b/providers/requesty/models/openai/gpt-4o-2024-11-20.toml new file mode 100644 index 00000000000..c807afdbe17 --- /dev/null +++ b/providers/requesty/models/openai/gpt-4o-2024-11-20.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4o-2024-11-20" + +[cost] +input = 2.5 +output = 10 +cache_read = 1.25 diff --git a/providers/requesty/models/openai/gpt-4o-mini.toml b/providers/requesty/models/openai/gpt-4o-mini.toml index cbf5bc60925..77ad4f0c39f 100644 --- a/providers/requesty/models/openai/gpt-4o-mini.toml +++ b/providers/requesty/models/openai/gpt-4o-mini.toml @@ -1,24 +1,7 @@ -name = "GPT-4o Mini" +base_model = "openai/gpt-4o-mini" description = "Compact GPT model for low-latency assistance and high-volume workloads" -family = "gpt-mini" -release_date = "2024-07-18" -last_updated = "2024-07-18" -attachment = true -reasoning = false -temperature = true -tool_call = true -knowledge = "2024-10" -open_weights = false [cost] input = 0.15 -output = 0.60 -cache_read = 0.08 - -[limit] -context = 128_000 -output = 16_384 - -[modalities] -input = ["text", "image"] -output = ["text"] +output = 0.6 +cache_read = 0.075 diff --git a/providers/requesty/models/openai/gpt-4o.toml b/providers/requesty/models/openai/gpt-4o.toml new file mode 100644 index 00000000000..1b57e520127 --- /dev/null +++ b/providers/requesty/models/openai/gpt-4o.toml @@ -0,0 +1,6 @@ +base_model = "openai/gpt-4o" + +[cost] +input = 2.5 +output = 10 +cache_read = 1.25 diff --git a/providers/requesty/models/openai/gpt-5-chat.toml b/providers/requesty/models/openai/gpt-5-chat.toml deleted file mode 100644 index 5d44e158b50..00000000000 --- a/providers/requesty/models/openai/gpt-5-chat.toml +++ /dev/null @@ -1,25 +0,0 @@ -name = "GPT-5 Chat (latest)" -description = "Chat-tuned GPT model for conversational assistance, writing, and tool workflows" -family = "gpt-codex" -release_date = "2025-08-07" -last_updated = "2025-08-07" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -knowledge = "2024-09-30" -tool_call = false -structured_output = true -open_weights = false - -[cost] -input = 1.25 -output = 10.00 - -[limit] -context = 400_000 -output = 128_000 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/providers/requesty/models/openai/gpt-5-codex.toml b/providers/requesty/models/openai/gpt-5-codex.toml deleted file mode 100644 index 3018b65d3eb..00000000000 --- a/providers/requesty/models/openai/gpt-5-codex.toml +++ /dev/null @@ -1,26 +0,0 @@ -name = "GPT-5 Codex" -description = "Coding-optimized GPT model for repository edits, reviews, and agentic software work" -family = "gpt-codex" -release_date = "2025-09-15" -last_updated = "2025-09-15" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -knowledge = "2024-10-01" -tool_call = true -structured_output = true -open_weights = false - -[cost] -input = 1.25 -output = 10.00 -cache_read = 0.125 - -[limit] -context = 400_000 -output = 128_000 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/providers/requesty/models/openai/gpt-5-image.toml b/providers/requesty/models/openai/gpt-5-image.toml deleted file mode 100644 index 00a507972d6..00000000000 --- a/providers/requesty/models/openai/gpt-5-image.toml +++ /dev/null @@ -1,26 +0,0 @@ -name = "GPT-5 Image" -description = "Image model for prompt-driven generation, editing, and visual design workflows" -family = "gpt" -release_date = "2025-10-14" -last_updated = "2025-10-14" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -knowledge = "2024-10-01" -tool_call = true -structured_output = true -open_weights = false - -[cost] -input = 5.00 -output = 10.00 -cache_read = 1.25 - -[limit] -context = 400_000 -output = 128_000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text", "image"] diff --git a/providers/requesty/models/openai/gpt-5-mini.toml b/providers/requesty/models/openai/gpt-5-mini.toml index 62e297e5c28..1d19c8a9ff6 100644 --- a/providers/requesty/models/openai/gpt-5-mini.toml +++ b/providers/requesty/models/openai/gpt-5-mini.toml @@ -1,25 +1,11 @@ -name = "GPT-5 Mini" +base_model = "openai/gpt-5-mini" description = "Compact GPT model for low-latency assistance and high-volume workloads" -family = "gpt-mini" -release_date = "2025-08-07" -last_updated = "2025-08-07" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = false -knowledge = "2024-05-30" -tool_call = true -open_weights = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] [cost] input = 0.25 -output = 2.00 -cache_read = 0.03 - -[limit] -context = 128_000 -output = 32_000 - -[modalities] -input = ["text", "image"] -output = ["text"] +output = 2 +cache_read = 0.025 diff --git a/providers/requesty/models/openai/gpt-5-mini:flex.toml b/providers/requesty/models/openai/gpt-5-mini:flex.toml new file mode 100644 index 00000000000..c6ca4ad0238 --- /dev/null +++ b/providers/requesty/models/openai/gpt-5-mini:flex.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.125 +output = 1 +cache_read = 0.0125 diff --git a/providers/requesty/models/openai/gpt-5-mini:priority.toml b/providers/requesty/models/openai/gpt-5-mini:priority.toml new file mode 100644 index 00000000000..474f55c3c10 --- /dev/null +++ b/providers/requesty/models/openai/gpt-5-mini:priority.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.45 +output = 3.6 +cache_read = 0.045 diff --git a/providers/requesty/models/openai/gpt-5-nano.toml b/providers/requesty/models/openai/gpt-5-nano.toml index 316044c9998..0b2b35c5dea 100644 --- a/providers/requesty/models/openai/gpt-5-nano.toml +++ b/providers/requesty/models/openai/gpt-5-nano.toml @@ -1,25 +1,11 @@ -name = "GPT-5 Nano" +base_model = "openai/gpt-5-nano" description = "Compact GPT model for low-latency assistance and high-volume workloads" -family = "gpt-nano" -release_date = "2025-08-07" -last_updated = "2025-08-07" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = false -knowledge = "2024-05-30" -tool_call = true -open_weights = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] [cost] input = 0.05 -output = 0.40 -cache_read = 0.01 - -[limit] -context = 16_000 -output = 4_000 - -[modalities] -input = ["text"] -output = ["text"] +output = 0.4 +cache_read = 0.005 diff --git a/providers/requesty/models/openai/gpt-5-nano:flex.toml b/providers/requesty/models/openai/gpt-5-nano:flex.toml new file mode 100644 index 00000000000..6a3577769f6 --- /dev/null +++ b/providers/requesty/models/openai/gpt-5-nano:flex.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5-nano" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.025 +output = 0.2 +cache_read = 0.0025 diff --git a/providers/requesty/models/openai/gpt-5-pro.toml b/providers/requesty/models/openai/gpt-5-pro.toml deleted file mode 100644 index 17b5915dff2..00000000000 --- a/providers/requesty/models/openai/gpt-5-pro.toml +++ /dev/null @@ -1,8 +0,0 @@ -base_model = "openai/gpt-5-pro" -base_model_omit = ["limit.input"] - -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] - -[cost] -input = 15 -output = 120 diff --git a/providers/requesty/models/openai/gpt-5.1-codex-max.toml b/providers/requesty/models/openai/gpt-5.1-codex-max.toml deleted file mode 100644 index 728fdd8a772..00000000000 --- a/providers/requesty/models/openai/gpt-5.1-codex-max.toml +++ /dev/null @@ -1,26 +0,0 @@ -name = "GPT-5.1-Codex-Max" -description = "Coding-optimized GPT model for repository edits, reviews, and agentic software work" -family = "gpt-codex" -release_date = "2025-11-13" -last_updated = "2025-11-13" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -knowledge = "2024-09-30" -tool_call = true -structured_output = true -open_weights = false - -[cost] -input = 1.10 -output = 9.00 -cache_read = 0.11 - -[limit] -context = 400_000 -output = 128_000 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/providers/requesty/models/openai/gpt-5.1-codex-mini.toml b/providers/requesty/models/openai/gpt-5.1-codex-mini.toml deleted file mode 100644 index 2c6e08105b2..00000000000 --- a/providers/requesty/models/openai/gpt-5.1-codex-mini.toml +++ /dev/null @@ -1,26 +0,0 @@ -name = "GPT-5.1-Codex-Mini" -description = "Coding-optimized GPT model for repository edits, reviews, and agentic software work" -family = "gpt-codex" -release_date = "2025-11-13" -last_updated = "2025-11-13" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -knowledge = "2024-09-30" -tool_call = true -structured_output = true -open_weights = false - -[cost] -input = 0.25 -output = 2.00 -cache_read = 0.025 - -[limit] -context = 400_000 -output = 100_000 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/providers/requesty/models/openai/gpt-5.1-codex.toml b/providers/requesty/models/openai/gpt-5.1-codex.toml deleted file mode 100644 index 958bd20ded7..00000000000 --- a/providers/requesty/models/openai/gpt-5.1-codex.toml +++ /dev/null @@ -1,26 +0,0 @@ -name = "GPT-5.1-Codex" -description = "Coding-optimized GPT model for repository edits, reviews, and agentic software work" -family = "gpt-codex" -release_date = "2025-11-13" -last_updated = "2025-11-13" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -knowledge = "2024-09-30" -tool_call = true -structured_output = true -open_weights = false - -[cost] -input = 1.25 -output = 10.00 -cache_read = 0.125 - -[limit] -context = 400_000 -output = 128_000 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/providers/requesty/models/openai/gpt-5.1.toml b/providers/requesty/models/openai/gpt-5.1.toml index d2c6bc22e61..fd03797397f 100644 --- a/providers/requesty/models/openai/gpt-5.1.toml +++ b/providers/requesty/models/openai/gpt-5.1.toml @@ -1,26 +1,11 @@ -name = "GPT-5.1" +base_model = "openai/gpt-5.1" description = "GPT model for general reasoning, writing, coding, and tool-assisted tasks" -family = "gpt" -release_date = "2025-11-13" -last_updated = "2025-11-13" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -knowledge = "2024-09-30" -tool_call = true -structured_output = true -open_weights = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] [cost] input = 1.25 -output = 10.00 +output = 10 cache_read = 0.125 - -[limit] -context = 400_000 -output = 128_000 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/providers/requesty/models/openai/gpt-5.2-codex.toml b/providers/requesty/models/openai/gpt-5.2-codex.toml deleted file mode 100644 index 942e7d0cf02..00000000000 --- a/providers/requesty/models/openai/gpt-5.2-codex.toml +++ /dev/null @@ -1,26 +0,0 @@ -name = "GPT-5.2-Codex" -description = "Coding-optimized GPT model for repository edits, reviews, and agentic software work" -family = "gpt-codex" -release_date = "2026-01-14" -last_updated = "2026-01-14" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -knowledge = "2025-08-31" -tool_call = true -structured_output = true -open_weights = false - -[cost] -input = 1.75 -output = 14.00 -cache_read = 0.175 - -[limit] -context = 400_000 -output = 128_000 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/providers/requesty/models/openai/gpt-5.2-pro.toml b/providers/requesty/models/openai/gpt-5.2-pro.toml deleted file mode 100644 index 5cd8bef1c36..00000000000 --- a/providers/requesty/models/openai/gpt-5.2-pro.toml +++ /dev/null @@ -1,25 +0,0 @@ -name = "GPT-5.2 Pro" -description = "Frontier GPT model for professional reasoning, coding, and multimodal work" -family = "gpt-pro" -release_date = "2025-12-11" -last_updated = "2025-12-11" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = false -knowledge = "2025-08-31" -tool_call = true -structured_output = true -open_weights = false - -[cost] -input = 21.00 -output = 168.00 - -[limit] -context = 400_000 -output = 128_000 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/providers/requesty/models/openai/gpt-5.2.toml b/providers/requesty/models/openai/gpt-5.2.toml index 57b482d6bf0..82a7714421e 100644 --- a/providers/requesty/models/openai/gpt-5.2.toml +++ b/providers/requesty/models/openai/gpt-5.2.toml @@ -1,7 +1,9 @@ base_model = "openai/gpt-5.2" base_model_omit = ["limit.input"] -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] [cost] input = 1.75 diff --git a/providers/requesty/models/openai/gpt-5.3-codex.toml b/providers/requesty/models/openai/gpt-5.3-codex.toml deleted file mode 100644 index f3994fed6bd..00000000000 --- a/providers/requesty/models/openai/gpt-5.3-codex.toml +++ /dev/null @@ -1,26 +0,0 @@ -name = "GPT-5.3-Codex" -description = "Coding-optimized GPT model for repository edits, reviews, and agentic software work" -family = "gpt-codex" -release_date = "2026-02-24" -last_updated = "2026-02-24" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = false -knowledge = "2025-08-31" -tool_call = true -structured_output = true -open_weights = false - -[cost] -input = 1.75 -output = 14.00 -cache_read = 0.175 - -[limit] -context = 400_000 -output = 128_000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] diff --git a/providers/requesty/models/openai/gpt-5.4-mini.toml b/providers/requesty/models/openai/gpt-5.4-mini.toml new file mode 100644 index 00000000000..be3542d6282 --- /dev/null +++ b/providers/requesty/models/openai/gpt-5.4-mini.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.75 +output = 4.5 +cache_read = 0.075 diff --git a/providers/requesty/models/openai/gpt-5.4-nano.toml b/providers/requesty/models/openai/gpt-5.4-nano.toml new file mode 100644 index 00000000000..223166b82f9 --- /dev/null +++ b/providers/requesty/models/openai/gpt-5.4-nano.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.4-nano" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.2 +output = 1.25 +cache_read = 0.02 diff --git a/providers/requesty/models/openai/gpt-5.4-pro.toml b/providers/requesty/models/openai/gpt-5.4-pro.toml deleted file mode 100644 index d59ad0a5225..00000000000 --- a/providers/requesty/models/openai/gpt-5.4-pro.toml +++ /dev/null @@ -1,27 +0,0 @@ -name = "GPT-5.4 Pro" -description = "Frontier GPT model for professional reasoning, coding, and multimodal work" -family = "gpt-pro" -release_date = "2026-03-05" -last_updated = "2026-03-05" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = false -knowledge = "2025-08-31" -tool_call = true -structured_output = false -open_weights = false - -[cost] -input = 30.00 -output = 180.00 -cache_read = 30.00 - -[limit] -context = 1_050_000 -input = 922_000 -output = 128_000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] diff --git a/providers/requesty/models/openai/gpt-5.4.toml b/providers/requesty/models/openai/gpt-5.4.toml index c073607de90..79414bc5379 100644 --- a/providers/requesty/models/openai/gpt-5.4.toml +++ b/providers/requesty/models/openai/gpt-5.4.toml @@ -1,6 +1,8 @@ base_model = "openai/gpt-5.4" -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] [cost] input = 2.5 diff --git a/providers/requesty/models/openai/gpt-5.5.toml b/providers/requesty/models/openai/gpt-5.5.toml new file mode 100644 index 00000000000..b36d2d62074 --- /dev/null +++ b/providers/requesty/models/openai/gpt-5.5.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 30 +cache_read = 0.5 diff --git a/providers/requesty/models/openai/gpt-5.6-luna.toml b/providers/requesty/models/openai/gpt-5.6-luna.toml new file mode 100644 index 00000000000..08a1a8839f0 --- /dev/null +++ b/providers/requesty/models/openai/gpt-5.6-luna.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-luna" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1 +output = 6 +cache_read = 0.1 diff --git a/providers/requesty/models/openai/gpt-5.6-sol.toml b/providers/requesty/models/openai/gpt-5.6-sol.toml new file mode 100644 index 00000000000..edccc583108 --- /dev/null +++ b/providers/requesty/models/openai/gpt-5.6-sol.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-sol" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 30 +cache_read = 0.5 diff --git a/providers/requesty/models/openai/gpt-5.6-terra.toml b/providers/requesty/models/openai/gpt-5.6-terra.toml new file mode 100644 index 00000000000..714e3afa796 --- /dev/null +++ b/providers/requesty/models/openai/gpt-5.6-terra.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5.6-terra" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.5 +output = 15 +cache_read = 0.25 diff --git a/providers/requesty/models/openai/gpt-5.toml b/providers/requesty/models/openai/gpt-5.toml index 390940407f0..983ad70a94f 100644 --- a/providers/requesty/models/openai/gpt-5.toml +++ b/providers/requesty/models/openai/gpt-5.toml @@ -1,25 +1,11 @@ -name = "GPT-5" +base_model = "openai/gpt-5" description = "Speech generation model for controllable voice, narration, and audio delivery" -family = "gpt" -release_date = "2025-08-07" -last_updated = "2025-08-07" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = false -knowledge = "2024-09-30" -tool_call = true -open_weights = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] [cost] input = 1.25 -output = 10.00 -cache_read = 0.13 - -[limit] -context = 400_000 -output = 128_000 - -[modalities] -input = ["text", "audio", "image", "video"] -output = ["text", "audio", "image"] +output = 10 +cache_read = 0.125 diff --git a/providers/requesty/models/openai/gpt-5:flex.toml b/providers/requesty/models/openai/gpt-5:flex.toml new file mode 100644 index 00000000000..02b3fed998a --- /dev/null +++ b/providers/requesty/models/openai/gpt-5:flex.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.625 +output = 5 +cache_read = 0.0625 diff --git a/providers/requesty/models/openai/gpt-5:priority.toml b/providers/requesty/models/openai/gpt-5:priority.toml new file mode 100644 index 00000000000..874d3d973a7 --- /dev/null +++ b/providers/requesty/models/openai/gpt-5:priority.toml @@ -0,0 +1,10 @@ +base_model = "openai/gpt-5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.5 +output = 20 +cache_read = 0.25 diff --git a/providers/requesty/models/openai/o1.toml b/providers/requesty/models/openai/o1.toml new file mode 100644 index 00000000000..6551b9d0d79 --- /dev/null +++ b/providers/requesty/models/openai/o1.toml @@ -0,0 +1,10 @@ +base_model = "openai/o1" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 15 +output = 60 +cache_read = 7.5 diff --git a/providers/requesty/models/openai/o1:high.toml b/providers/requesty/models/openai/o1:high.toml new file mode 100644 index 00000000000..6551b9d0d79 --- /dev/null +++ b/providers/requesty/models/openai/o1:high.toml @@ -0,0 +1,10 @@ +base_model = "openai/o1" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 15 +output = 60 +cache_read = 7.5 diff --git a/providers/requesty/models/openai/o1:low.toml b/providers/requesty/models/openai/o1:low.toml new file mode 100644 index 00000000000..6551b9d0d79 --- /dev/null +++ b/providers/requesty/models/openai/o1:low.toml @@ -0,0 +1,10 @@ +base_model = "openai/o1" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 15 +output = 60 +cache_read = 7.5 diff --git a/providers/requesty/models/openai/o1:medium.toml b/providers/requesty/models/openai/o1:medium.toml new file mode 100644 index 00000000000..6551b9d0d79 --- /dev/null +++ b/providers/requesty/models/openai/o1:medium.toml @@ -0,0 +1,10 @@ +base_model = "openai/o1" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 15 +output = 60 +cache_read = 7.5 diff --git a/providers/requesty/models/openai/o3-mini.toml b/providers/requesty/models/openai/o3-mini.toml new file mode 100644 index 00000000000..858665dd751 --- /dev/null +++ b/providers/requesty/models/openai/o3-mini.toml @@ -0,0 +1,10 @@ +base_model = "openai/o3-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 4.4 +cache_read = 0.55 diff --git a/providers/requesty/models/openai/o3-mini:high.toml b/providers/requesty/models/openai/o3-mini:high.toml new file mode 100644 index 00000000000..858665dd751 --- /dev/null +++ b/providers/requesty/models/openai/o3-mini:high.toml @@ -0,0 +1,10 @@ +base_model = "openai/o3-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 4.4 +cache_read = 0.55 diff --git a/providers/requesty/models/openai/o3-mini:low.toml b/providers/requesty/models/openai/o3-mini:low.toml new file mode 100644 index 00000000000..858665dd751 --- /dev/null +++ b/providers/requesty/models/openai/o3-mini:low.toml @@ -0,0 +1,10 @@ +base_model = "openai/o3-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 4.4 +cache_read = 0.55 diff --git a/providers/requesty/models/openai/o3-mini:medium.toml b/providers/requesty/models/openai/o3-mini:medium.toml new file mode 100644 index 00000000000..858665dd751 --- /dev/null +++ b/providers/requesty/models/openai/o3-mini:medium.toml @@ -0,0 +1,10 @@ +base_model = "openai/o3-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 4.4 +cache_read = 0.55 diff --git a/providers/requesty/models/openai/o3.toml b/providers/requesty/models/openai/o3.toml new file mode 100644 index 00000000000..fd6fe0264f8 --- /dev/null +++ b/providers/requesty/models/openai/o3.toml @@ -0,0 +1,10 @@ +base_model = "openai/o3" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2 +output = 8 +cache_read = 0.5 diff --git a/providers/requesty/models/openai/o3:flex.toml b/providers/requesty/models/openai/o3:flex.toml new file mode 100644 index 00000000000..698469a2c88 --- /dev/null +++ b/providers/requesty/models/openai/o3:flex.toml @@ -0,0 +1,10 @@ +base_model = "openai/o3" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1 +output = 4 +cache_read = 0.25 diff --git a/providers/requesty/models/openai/o4-mini.toml b/providers/requesty/models/openai/o4-mini.toml index b6f4f9b6601..8b464fb3816 100644 --- a/providers/requesty/models/openai/o4-mini.toml +++ b/providers/requesty/models/openai/o4-mini.toml @@ -1,25 +1,11 @@ -name = "o4 Mini" +base_model = "openai/o4-mini" description = "O-series reasoning model for hard analysis, math, coding, and planning" -family = "o-mini" -release_date = "2025-04-16" -last_updated = "2025-04-16" -attachment = true -reasoning = true -reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "high", "max"] }, { type = "budget_tokens" }] -temperature = true -tool_call = true -knowledge = "2024-06" -open_weights = false -[cost] -input = 1.10 -output = 4.40 -cache_read = 0.28 - -[limit] -context = 200_000 -output = 100_000 +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] -[modalities] -input = ["text", "image"] -output = ["text"] +[cost] +input = 1.1 +output = 4.4 +cache_read = 0.275 diff --git a/providers/requesty/models/openai/o4-mini:flex.toml b/providers/requesty/models/openai/o4-mini:flex.toml new file mode 100644 index 00000000000..bfc04d637e9 --- /dev/null +++ b/providers/requesty/models/openai/o4-mini:flex.toml @@ -0,0 +1,10 @@ +base_model = "openai/o4-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.55 +output = 2.2 +cache_read = 0.138 diff --git a/providers/requesty/models/openai/o4-mini:high.toml b/providers/requesty/models/openai/o4-mini:high.toml new file mode 100644 index 00000000000..1456870e216 --- /dev/null +++ b/providers/requesty/models/openai/o4-mini:high.toml @@ -0,0 +1,10 @@ +base_model = "openai/o4-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 4.4 +cache_read = 0.275 diff --git a/providers/requesty/models/openai/o4-mini:low.toml b/providers/requesty/models/openai/o4-mini:low.toml new file mode 100644 index 00000000000..1456870e216 --- /dev/null +++ b/providers/requesty/models/openai/o4-mini:low.toml @@ -0,0 +1,10 @@ +base_model = "openai/o4-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 4.4 +cache_read = 0.275 diff --git a/providers/requesty/models/openai/o4-mini:medium.toml b/providers/requesty/models/openai/o4-mini:medium.toml new file mode 100644 index 00000000000..1456870e216 --- /dev/null +++ b/providers/requesty/models/openai/o4-mini:medium.toml @@ -0,0 +1,10 @@ +base_model = "openai/o4-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 4.4 +cache_read = 0.275 diff --git a/providers/requesty/models/parasail/google/gemma-4-26B-A4B-it.toml b/providers/requesty/models/parasail/google/gemma-4-26B-A4B-it.toml new file mode 100644 index 00000000000..2d0748c3d68 --- /dev/null +++ b/providers/requesty/models/parasail/google/gemma-4-26B-A4B-it.toml @@ -0,0 +1,10 @@ +base_model = "google/gemma-4-26b-a4b-it" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.13 +output = 0.4 +cache_read = 0.05 diff --git a/providers/requesty/models/parasail/kimi-k2.7-code.toml b/providers/requesty/models/parasail/kimi-k2.7-code.toml new file mode 100644 index 00000000000..a918d418229 --- /dev/null +++ b/providers/requesty/models/parasail/kimi-k2.7-code.toml @@ -0,0 +1,10 @@ +base_model = "moonshotai/kimi-k2.7-code" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.75 +output = 3.5 +cache_read = 0.16 diff --git a/providers/requesty/models/perplexity/sonar-pro.toml b/providers/requesty/models/perplexity/sonar-pro.toml new file mode 100644 index 00000000000..7872b04827c --- /dev/null +++ b/providers/requesty/models/perplexity/sonar-pro.toml @@ -0,0 +1,10 @@ +base_model = "perplexity/sonar-pro" +structured_output = true + +[cost] +input = 3 +output = 15 +cache_read = 3 + +[limit] +context = 204_800 diff --git a/providers/requesty/models/perplexity/sonar-reasoning-pro.toml b/providers/requesty/models/perplexity/sonar-reasoning-pro.toml new file mode 100644 index 00000000000..c28399478a7 --- /dev/null +++ b/providers/requesty/models/perplexity/sonar-reasoning-pro.toml @@ -0,0 +1,15 @@ +base_model = "perplexity/sonar-reasoning-pro" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2 +output = 8 +cache_read = 2 + +[limit] +context = 131_072 +output = 8_192 diff --git a/providers/requesty/models/perplexity/sonar.toml b/providers/requesty/models/perplexity/sonar.toml new file mode 100644 index 00000000000..e891e991d39 --- /dev/null +++ b/providers/requesty/models/perplexity/sonar.toml @@ -0,0 +1,11 @@ +base_model = "perplexity/sonar" +structured_output = true + +[cost] +input = 1 +output = 1 +cache_read = 1 + +[limit] +context = 131_072 +output = 8_192 diff --git a/providers/requesty/models/poolside/laguna-m.1.toml b/providers/requesty/models/poolside/laguna-m.1.toml new file mode 100644 index 00000000000..a94699e009c --- /dev/null +++ b/providers/requesty/models/poolside/laguna-m.1.toml @@ -0,0 +1,12 @@ +base_model = "poolside/laguna-m.1" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0 +output = 0 + +[limit] +context = 32_768 diff --git a/providers/requesty/models/poolside/laguna-xs.2.toml b/providers/requesty/models/poolside/laguna-xs.2.toml new file mode 100644 index 00000000000..97fbcfff977 --- /dev/null +++ b/providers/requesty/models/poolside/laguna-xs.2.toml @@ -0,0 +1,12 @@ +base_model = "poolside/laguna-xs.2" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0 +output = 0 + +[limit] +context = 32_768 diff --git a/providers/requesty/models/sakana/fugu-ultra.toml b/providers/requesty/models/sakana/fugu-ultra.toml new file mode 100644 index 00000000000..b139c43e474 --- /dev/null +++ b/providers/requesty/models/sakana/fugu-ultra.toml @@ -0,0 +1,14 @@ +base_model = "sakana/fugu-ultra" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 30 +cache_read = 0.5 + +[limit] +context = 1_048_576 +output = 131_072 diff --git a/providers/requesty/models/sference/deepseek-v4-flash.toml b/providers/requesty/models/sference/deepseek-v4-flash.toml new file mode 100644 index 00000000000..425f3fb7b23 --- /dev/null +++ b/providers/requesty/models/sference/deepseek-v4-flash.toml @@ -0,0 +1,14 @@ +base_model = "deepseek/deepseek-v4-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.14 +output = 0.28 +cache_read = 0.07 + +[limit] +context = 1_048_576 +output = 131_072 diff --git a/providers/requesty/models/sference/glm-5.2.toml b/providers/requesty/models/sference/glm-5.2.toml new file mode 100644 index 00000000000..8be99012975 --- /dev/null +++ b/providers/requesty/models/sference/glm-5.2.toml @@ -0,0 +1,13 @@ +base_model = "zhipuai/glm-5.2" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.2 +output = 4.2 +cache_read = 0.26 + +[limit] +context = 1_048_576 diff --git a/providers/requesty/models/sference/kimi-k3.toml b/providers/requesty/models/sference/kimi-k3.toml new file mode 100644 index 00000000000..51396af5aee --- /dev/null +++ b/providers/requesty/models/sference/kimi-k3.toml @@ -0,0 +1,13 @@ +base_model = "moonshotai/kimi-k3" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.25 +output = 11.25 +cache_read = 0.225 + +[limit] +output = 262_144 diff --git a/providers/requesty/models/tensorx/deepseek-v4-flash.toml b/providers/requesty/models/tensorx/deepseek-v4-flash.toml new file mode 100644 index 00000000000..6ae154c7d17 --- /dev/null +++ b/providers/requesty/models/tensorx/deepseek-v4-flash.toml @@ -0,0 +1,14 @@ +base_model = "deepseek/deepseek-v4-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.15 +output = 0.3 +cache_read = 0.04 + +[limit] +context = 1_048_576 +output = 1_048_576 diff --git a/providers/requesty/models/tensorx/deepseek-v4-pro.toml b/providers/requesty/models/tensorx/deepseek-v4-pro.toml new file mode 100644 index 00000000000..ce74fb47942 --- /dev/null +++ b/providers/requesty/models/tensorx/deepseek-v4-pro.toml @@ -0,0 +1,14 @@ +base_model = "deepseek/deepseek-v4-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.75 +output = 3.5 +cache_read = 0.44 + +[limit] +context = 1_048_576 +output = 1_048_576 diff --git a/providers/requesty/models/tensorx/glm-5.2.toml b/providers/requesty/models/tensorx/glm-5.2.toml new file mode 100644 index 00000000000..fca8b61ad72 --- /dev/null +++ b/providers/requesty/models/tensorx/glm-5.2.toml @@ -0,0 +1,14 @@ +base_model = "zhipuai/glm-5.2" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.5 +output = 4.5 +cache_read = 0.38 + +[limit] +context = 1_048_576 +output = 1_048_576 diff --git a/providers/requesty/models/tensorx/kimi-k2.7-code.toml b/providers/requesty/models/tensorx/kimi-k2.7-code.toml new file mode 100644 index 00000000000..7e05164ac5f --- /dev/null +++ b/providers/requesty/models/tensorx/kimi-k2.7-code.toml @@ -0,0 +1,10 @@ +base_model = "moonshotai/kimi-k2.7-code" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 4.5 +cache_read = 0.31 diff --git a/providers/requesty/models/tensorx/kimi-k3.toml b/providers/requesty/models/tensorx/kimi-k3.toml new file mode 100644 index 00000000000..423df78bb91 --- /dev/null +++ b/providers/requesty/models/tensorx/kimi-k3.toml @@ -0,0 +1,13 @@ +base_model = "moonshotai/kimi-k3" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3 +output = 15 +cache_read = 0.75 + +[limit] +output = 262_144 diff --git a/providers/requesty/models/tensorx/minimax-m3.toml b/providers/requesty/models/tensorx/minimax-m3.toml new file mode 100644 index 00000000000..cc0c3c7ac9f --- /dev/null +++ b/providers/requesty/models/tensorx/minimax-m3.toml @@ -0,0 +1,15 @@ +base_model = "minimax/MiniMax-M3" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.4 +output = 2 +cache_read = 0.1 + +[limit] +context = 1_048_576 +output = 1_048_576 diff --git a/providers/requesty/models/thinkingmachines/inkling.toml b/providers/requesty/models/thinkingmachines/inkling.toml new file mode 100644 index 00000000000..7016e26f354 --- /dev/null +++ b/providers/requesty/models/thinkingmachines/inkling.toml @@ -0,0 +1,15 @@ +base_model = "thinkingmachines/inkling" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.87 +output = 4.68 +cache_read = 0.374 + +[limit] +context = 65_536 +output = 32_768 diff --git a/providers/requesty/models/vertex/claude-fable-5.toml b/providers/requesty/models/vertex/claude-fable-5.toml new file mode 100644 index 00000000000..c10753af62c --- /dev/null +++ b/providers/requesty/models/vertex/claude-fable-5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-fable-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 10 +output = 50 +cache_read = 1 +cache_write = 12.5 diff --git a/providers/requesty/models/vertex/claude-fable-5@eu.toml b/providers/requesty/models/vertex/claude-fable-5@eu.toml new file mode 100644 index 00000000000..68e17072888 --- /dev/null +++ b/providers/requesty/models/vertex/claude-fable-5@eu.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-fable-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 11 +output = 55 +cache_read = 1.1 +cache_write = 13.75 diff --git a/providers/requesty/models/vertex/claude-haiku-4-5.toml b/providers/requesty/models/vertex/claude-haiku-4-5.toml new file mode 100644 index 00000000000..895510c3d47 --- /dev/null +++ b/providers/requesty/models/vertex/claude-haiku-4-5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-haiku-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1 +output = 5 +cache_read = 0.1 +cache_write = 1.25 diff --git a/providers/requesty/models/vertex/claude-haiku-4-5@europe-west1.toml b/providers/requesty/models/vertex/claude-haiku-4-5@europe-west1.toml new file mode 100644 index 00000000000..9569ab641f8 --- /dev/null +++ b/providers/requesty/models/vertex/claude-haiku-4-5@europe-west1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-haiku-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 5.5 +cache_read = 0.11 +cache_write = 1.375 diff --git a/providers/requesty/models/vertex/claude-haiku-4-5@us-east5.toml b/providers/requesty/models/vertex/claude-haiku-4-5@us-east5.toml new file mode 100644 index 00000000000..9569ab641f8 --- /dev/null +++ b/providers/requesty/models/vertex/claude-haiku-4-5@us-east5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-haiku-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.1 +output = 5.5 +cache_read = 0.11 +cache_write = 1.375 diff --git a/providers/requesty/models/vertex/claude-opus-4-1.toml b/providers/requesty/models/vertex/claude-opus-4-1.toml new file mode 100644 index 00000000000..b85c3773181 --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-4-1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-1" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 15 +output = 75 +cache_read = 1.5 +cache_write = 18.75 diff --git a/providers/requesty/models/vertex/claude-opus-4-1@us-east5.toml b/providers/requesty/models/vertex/claude-opus-4-1@us-east5.toml new file mode 100644 index 00000000000..b85c3773181 --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-4-1@us-east5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-1" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 15 +output = 75 +cache_read = 1.5 +cache_write = 18.75 diff --git a/providers/requesty/models/vertex/claude-opus-4-5.toml b/providers/requesty/models/vertex/claude-opus-4-5.toml new file mode 100644 index 00000000000..9d8db2e267f --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-4-5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 25 +cache_read = 0.5 +cache_write = 6.25 diff --git a/providers/requesty/models/vertex/claude-opus-4-5@europe-west1.toml b/providers/requesty/models/vertex/claude-opus-4-5@europe-west1.toml new file mode 100644 index 00000000000..38eabdfbecb --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-4-5@europe-west1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/vertex/claude-opus-4-5@us-east5.toml b/providers/requesty/models/vertex/claude-opus-4-5@us-east5.toml new file mode 100644 index 00000000000..38eabdfbecb --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-4-5@us-east5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.875 diff --git a/providers/requesty/models/vertex/claude-opus-4-6.toml b/providers/requesty/models/vertex/claude-opus-4-6.toml new file mode 100644 index 00000000000..4b8468b293d --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-4-6.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-6" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 25 +cache_read = 0.5 +cache_write = 6.25 diff --git a/providers/requesty/models/vertex/claude-opus-4-6@europe-west1.toml b/providers/requesty/models/vertex/claude-opus-4-6@europe-west1.toml new file mode 100644 index 00000000000..437ea6d5d88 --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-4-6@europe-west1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-6" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.88 diff --git a/providers/requesty/models/vertex/claude-opus-4-6@us-east5.toml b/providers/requesty/models/vertex/claude-opus-4-6@us-east5.toml new file mode 100644 index 00000000000..437ea6d5d88 --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-4-6@us-east5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-6" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.88 diff --git a/providers/requesty/models/vertex/claude-opus-4-7.toml b/providers/requesty/models/vertex/claude-opus-4-7.toml new file mode 100644 index 00000000000..4edff5914b5 --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-4-7.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-7" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 25 +cache_read = 0.5 +cache_write = 6.25 diff --git a/providers/requesty/models/vertex/claude-opus-4-7@eu.toml b/providers/requesty/models/vertex/claude-opus-4-7@eu.toml new file mode 100644 index 00000000000..d94e2ba8cdb --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-4-7@eu.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-7" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.88 diff --git a/providers/requesty/models/vertex/claude-opus-4-7@us.toml b/providers/requesty/models/vertex/claude-opus-4-7@us.toml new file mode 100644 index 00000000000..d94e2ba8cdb --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-4-7@us.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-7" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.88 diff --git a/providers/requesty/models/vertex/claude-opus-4-8.toml b/providers/requesty/models/vertex/claude-opus-4-8.toml new file mode 100644 index 00000000000..d5cf84bf456 --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-4-8.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-8" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 25 +cache_read = 0.5 +cache_write = 6.25 diff --git a/providers/requesty/models/vertex/claude-opus-4-8@eu.toml b/providers/requesty/models/vertex/claude-opus-4-8@eu.toml new file mode 100644 index 00000000000..c3ea6aebb77 --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-4-8@eu.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-8" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.88 diff --git a/providers/requesty/models/vertex/claude-opus-4-8@us.toml b/providers/requesty/models/vertex/claude-opus-4-8@us.toml new file mode 100644 index 00000000000..c3ea6aebb77 --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-4-8@us.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-4-8" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.88 diff --git a/providers/requesty/models/vertex/claude-opus-5.toml b/providers/requesty/models/vertex/claude-opus-5.toml new file mode 100644 index 00000000000..143e01133a7 --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5 +output = 25 +cache_read = 0.5 +cache_write = 6.25 diff --git a/providers/requesty/models/vertex/claude-opus-5@eu.toml b/providers/requesty/models/vertex/claude-opus-5@eu.toml new file mode 100644 index 00000000000..088919587d0 --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-5@eu.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.88 diff --git a/providers/requesty/models/vertex/claude-opus-5@us.toml b/providers/requesty/models/vertex/claude-opus-5@us.toml new file mode 100644 index 00000000000..088919587d0 --- /dev/null +++ b/providers/requesty/models/vertex/claude-opus-5@us.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-opus-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 5.5 +output = 27.5 +cache_read = 0.55 +cache_write = 6.88 diff --git a/providers/requesty/models/vertex/claude-sonnet-4-5.toml b/providers/requesty/models/vertex/claude-sonnet-4-5.toml new file mode 100644 index 00000000000..d0c775ffe7e --- /dev/null +++ b/providers/requesty/models/vertex/claude-sonnet-4-5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3 +output = 15 +cache_read = 0.3 +cache_write = 3.75 diff --git a/providers/requesty/models/vertex/claude-sonnet-4-5@europe-west1.toml b/providers/requesty/models/vertex/claude-sonnet-4-5@europe-west1.toml new file mode 100644 index 00000000000..3fd53d78448 --- /dev/null +++ b/providers/requesty/models/vertex/claude-sonnet-4-5@europe-west1.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.33 +cache_write = 4.13 diff --git a/providers/requesty/models/vertex/claude-sonnet-4-5@us-east5.toml b/providers/requesty/models/vertex/claude-sonnet-4-5@us-east5.toml new file mode 100644 index 00000000000..3fd53d78448 --- /dev/null +++ b/providers/requesty/models/vertex/claude-sonnet-4-5@us-east5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-4-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3.3 +output = 16.5 +cache_read = 0.33 +cache_write = 4.13 diff --git a/providers/requesty/models/vertex/claude-sonnet-4-6.toml b/providers/requesty/models/vertex/claude-sonnet-4-6.toml new file mode 100644 index 00000000000..7f019a771d8 --- /dev/null +++ b/providers/requesty/models/vertex/claude-sonnet-4-6.toml @@ -0,0 +1,15 @@ +base_model = "anthropic/claude-sonnet-4-6" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3 +output = 15 +cache_read = 0.3 +cache_write = 3.75 + +[limit] +output = 128_000 diff --git a/providers/requesty/models/vertex/claude-sonnet-4-6@europe-west1.toml b/providers/requesty/models/vertex/claude-sonnet-4-6@europe-west1.toml new file mode 100644 index 00000000000..7f019a771d8 --- /dev/null +++ b/providers/requesty/models/vertex/claude-sonnet-4-6@europe-west1.toml @@ -0,0 +1,15 @@ +base_model = "anthropic/claude-sonnet-4-6" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3 +output = 15 +cache_read = 0.3 +cache_write = 3.75 + +[limit] +output = 128_000 diff --git a/providers/requesty/models/vertex/claude-sonnet-4-6@us-east5.toml b/providers/requesty/models/vertex/claude-sonnet-4-6@us-east5.toml new file mode 100644 index 00000000000..7f019a771d8 --- /dev/null +++ b/providers/requesty/models/vertex/claude-sonnet-4-6@us-east5.toml @@ -0,0 +1,15 @@ +base_model = "anthropic/claude-sonnet-4-6" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 3 +output = 15 +cache_read = 0.3 +cache_write = 3.75 + +[limit] +output = 128_000 diff --git a/providers/requesty/models/vertex/claude-sonnet-5.toml b/providers/requesty/models/vertex/claude-sonnet-5.toml new file mode 100644 index 00000000000..6f4bad93f23 --- /dev/null +++ b/providers/requesty/models/vertex/claude-sonnet-5.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2 +output = 10 +cache_read = 0.2 +cache_write = 2.5 diff --git a/providers/requesty/models/vertex/claude-sonnet-5@eu.toml b/providers/requesty/models/vertex/claude-sonnet-5@eu.toml new file mode 100644 index 00000000000..8f0d6c7dca5 --- /dev/null +++ b/providers/requesty/models/vertex/claude-sonnet-5@eu.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.2 +output = 11 +cache_read = 0.22 +cache_write = 2.75 diff --git a/providers/requesty/models/vertex/claude-sonnet-5@us.toml b/providers/requesty/models/vertex/claude-sonnet-5@us.toml new file mode 100644 index 00000000000..8f0d6c7dca5 --- /dev/null +++ b/providers/requesty/models/vertex/claude-sonnet-5@us.toml @@ -0,0 +1,12 @@ +base_model = "anthropic/claude-sonnet-5" +structured_output = true + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2.2 +output = 11 +cache_read = 0.22 +cache_write = 2.75 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-image.toml b/providers/requesty/models/vertex/gemini-2.5-flash-image.toml new file mode 100644 index 00000000000..9fd77aabafd --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-image.toml @@ -0,0 +1,17 @@ +base_model = "google/gemini-2.5-flash-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.3 +cache_write = 2.5 + +[limit] +context = 1_048_576 +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-central2.toml b/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-central2.toml new file mode 100644 index 00000000000..9fd77aabafd --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-central2.toml @@ -0,0 +1,17 @@ +base_model = "google/gemini-2.5-flash-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.3 +cache_write = 2.5 + +[limit] +context = 1_048_576 +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-north1.toml b/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-north1.toml new file mode 100644 index 00000000000..9fd77aabafd --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-north1.toml @@ -0,0 +1,17 @@ +base_model = "google/gemini-2.5-flash-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.3 +cache_write = 2.5 + +[limit] +context = 1_048_576 +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-southwest1.toml b/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-southwest1.toml new file mode 100644 index 00000000000..9fd77aabafd --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-southwest1.toml @@ -0,0 +1,17 @@ +base_model = "google/gemini-2.5-flash-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.3 +cache_write = 2.5 + +[limit] +context = 1_048_576 +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-west1.toml b/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-west1.toml new file mode 100644 index 00000000000..9fd77aabafd --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-west1.toml @@ -0,0 +1,17 @@ +base_model = "google/gemini-2.5-flash-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.3 +cache_write = 2.5 + +[limit] +context = 1_048_576 +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-west4.toml b/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-west4.toml new file mode 100644 index 00000000000..9fd77aabafd --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-west4.toml @@ -0,0 +1,17 @@ +base_model = "google/gemini-2.5-flash-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.3 +cache_write = 2.5 + +[limit] +context = 1_048_576 +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-west8.toml b/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-west8.toml new file mode 100644 index 00000000000..9fd77aabafd --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-image@europe-west8.toml @@ -0,0 +1,17 @@ +base_model = "google/gemini-2.5-flash-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.3 +cache_write = 2.5 + +[limit] +context = 1_048_576 +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-image@us-central1.toml b/providers/requesty/models/vertex/gemini-2.5-flash-image@us-central1.toml new file mode 100644 index 00000000000..9fd77aabafd --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-image@us-central1.toml @@ -0,0 +1,17 @@ +base_model = "google/gemini-2.5-flash-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.3 +cache_write = 2.5 + +[limit] +context = 1_048_576 +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-image@us-east1.toml b/providers/requesty/models/vertex/gemini-2.5-flash-image@us-east1.toml new file mode 100644 index 00000000000..9fd77aabafd --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-image@us-east1.toml @@ -0,0 +1,17 @@ +base_model = "google/gemini-2.5-flash-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.3 +cache_write = 2.5 + +[limit] +context = 1_048_576 +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-image@us-east4.toml b/providers/requesty/models/vertex/gemini-2.5-flash-image@us-east4.toml new file mode 100644 index 00000000000..9fd77aabafd --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-image@us-east4.toml @@ -0,0 +1,17 @@ +base_model = "google/gemini-2.5-flash-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.3 +cache_write = 2.5 + +[limit] +context = 1_048_576 +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-image@us-east5.toml b/providers/requesty/models/vertex/gemini-2.5-flash-image@us-east5.toml new file mode 100644 index 00000000000..9fd77aabafd --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-image@us-east5.toml @@ -0,0 +1,17 @@ +base_model = "google/gemini-2.5-flash-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.3 +cache_write = 2.5 + +[limit] +context = 1_048_576 +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-image@us-south1.toml b/providers/requesty/models/vertex/gemini-2.5-flash-image@us-south1.toml new file mode 100644 index 00000000000..9fd77aabafd --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-image@us-south1.toml @@ -0,0 +1,17 @@ +base_model = "google/gemini-2.5-flash-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.3 +cache_write = 2.5 + +[limit] +context = 1_048_576 +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-image@us-west1.toml b/providers/requesty/models/vertex/gemini-2.5-flash-image@us-west1.toml new file mode 100644 index 00000000000..9fd77aabafd --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-image@us-west1.toml @@ -0,0 +1,17 @@ +base_model = "google/gemini-2.5-flash-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.3 +cache_write = 2.5 + +[limit] +context = 1_048_576 +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-image@us-west4.toml b/providers/requesty/models/vertex/gemini-2.5-flash-image@us-west4.toml new file mode 100644 index 00000000000..9fd77aabafd --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-image@us-west4.toml @@ -0,0 +1,17 @@ +base_model = "google/gemini-2.5-flash-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.3 +cache_write = 2.5 + +[limit] +context = 1_048_576 +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-lite.toml b/providers/requesty/models/vertex/gemini-2.5-flash-lite.toml new file mode 100644 index 00000000000..b00ec81e4f0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-lite.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.01 +cache_write = 0.18333 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-central2.toml b/providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-central2.toml new file mode 100644 index 00000000000..b00ec81e4f0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-central2.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.01 +cache_write = 0.18333 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-north1.toml b/providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-north1.toml new file mode 100644 index 00000000000..b00ec81e4f0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-north1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.01 +cache_write = 0.18333 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-west1.toml b/providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-west1.toml new file mode 100644 index 00000000000..b00ec81e4f0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-west1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.01 +cache_write = 0.18333 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-west4.toml b/providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-west4.toml new file mode 100644 index 00000000000..b00ec81e4f0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-west4.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.01 +cache_write = 0.18333 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-west8.toml b/providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-west8.toml new file mode 100644 index 00000000000..b00ec81e4f0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-lite@europe-west8.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.01 +cache_write = 0.18333 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-lite@us-central1.toml b/providers/requesty/models/vertex/gemini-2.5-flash-lite@us-central1.toml new file mode 100644 index 00000000000..b00ec81e4f0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-lite@us-central1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.01 +cache_write = 0.18333 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-lite@us-east1.toml b/providers/requesty/models/vertex/gemini-2.5-flash-lite@us-east1.toml new file mode 100644 index 00000000000..b00ec81e4f0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-lite@us-east1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.01 +cache_write = 0.18333 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-lite@us-east5.toml b/providers/requesty/models/vertex/gemini-2.5-flash-lite@us-east5.toml new file mode 100644 index 00000000000..b00ec81e4f0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-lite@us-east5.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.01 +cache_write = 0.18333 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-lite@us-south1.toml b/providers/requesty/models/vertex/gemini-2.5-flash-lite@us-south1.toml new file mode 100644 index 00000000000..b00ec81e4f0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-lite@us-south1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.01 +cache_write = 0.18333 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash-lite@us-west1.toml b/providers/requesty/models/vertex/gemini-2.5-flash-lite@us-west1.toml new file mode 100644 index 00000000000..b00ec81e4f0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash-lite@us-west1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.1 +output = 0.4 +cache_read = 0.01 +cache_write = 0.18333 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash.toml b/providers/requesty/models/vertex/gemini-2.5-flash.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash@europe-central2.toml b/providers/requesty/models/vertex/gemini-2.5-flash@europe-central2.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash@europe-central2.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash@europe-north1.toml b/providers/requesty/models/vertex/gemini-2.5-flash@europe-north1.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash@europe-north1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash@europe-west1.toml b/providers/requesty/models/vertex/gemini-2.5-flash@europe-west1.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash@europe-west1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash@europe-west4.toml b/providers/requesty/models/vertex/gemini-2.5-flash@europe-west4.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash@europe-west4.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash@europe-west8.toml b/providers/requesty/models/vertex/gemini-2.5-flash@europe-west8.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash@europe-west8.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash@us-central1.toml b/providers/requesty/models/vertex/gemini-2.5-flash@us-central1.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash@us-central1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash@us-east1.toml b/providers/requesty/models/vertex/gemini-2.5-flash@us-east1.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash@us-east1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash@us-east5.toml b/providers/requesty/models/vertex/gemini-2.5-flash@us-east5.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash@us-east5.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash@us-south1.toml b/providers/requesty/models/vertex/gemini-2.5-flash@us-south1.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash@us-south1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-flash@us-west1.toml b/providers/requesty/models/vertex/gemini-2.5-flash@us-west1.toml new file mode 100644 index 00000000000..a2ba61f5f9d --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-flash@us-west1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.075 +cache_write = 0.55 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-pro.toml b/providers/requesty/models/vertex/gemini-2.5-pro.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-pro.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-pro@europe-central2.toml b/providers/requesty/models/vertex/gemini-2.5-pro@europe-central2.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-pro@europe-central2.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-pro@europe-north1.toml b/providers/requesty/models/vertex/gemini-2.5-pro@europe-north1.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-pro@europe-north1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-pro@europe-west1.toml b/providers/requesty/models/vertex/gemini-2.5-pro@europe-west1.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-pro@europe-west1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-pro@europe-west4.toml b/providers/requesty/models/vertex/gemini-2.5-pro@europe-west4.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-pro@europe-west4.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-pro@europe-west8.toml b/providers/requesty/models/vertex/gemini-2.5-pro@europe-west8.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-pro@europe-west8.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-pro@us-central1.toml b/providers/requesty/models/vertex/gemini-2.5-pro@us-central1.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-pro@us-central1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-pro@us-east1.toml b/providers/requesty/models/vertex/gemini-2.5-pro@us-east1.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-pro@us-east1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-pro@us-east5.toml b/providers/requesty/models/vertex/gemini-2.5-pro@us-east5.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-pro@us-east5.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-pro@us-south1.toml b/providers/requesty/models/vertex/gemini-2.5-pro@us-south1.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-pro@us-south1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-2.5-pro@us-west1.toml b/providers/requesty/models/vertex/gemini-2.5-pro@us-west1.toml new file mode 100644 index 00000000000..a3c2696d9d0 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-2.5-pro@us-west1.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-2.5-pro" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 10 +cache_read = 0.31 +cache_write = 2.375 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-3-flash-preview.toml b/providers/requesty/models/vertex/gemini-3-flash-preview.toml new file mode 100644 index 00000000000..cbf7a12dcec --- /dev/null +++ b/providers/requesty/models/vertex/gemini-3-flash-preview.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-3-flash-preview" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.5 +output = 3 +cache_read = 0.05 +cache_write = 1 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-3-flash-preview:flex.toml b/providers/requesty/models/vertex/gemini-3-flash-preview:flex.toml new file mode 100644 index 00000000000..644857f0468 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-3-flash-preview:flex.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-3-flash-preview" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.25 +output = 1.5 +cache_read = 0.025 +cache_write = 0.5 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-3-pro-image.toml b/providers/requesty/models/vertex/gemini-3-pro-image.toml new file mode 100644 index 00000000000..cabe2d077eb --- /dev/null +++ b/providers/requesty/models/vertex/gemini-3-pro-image.toml @@ -0,0 +1,16 @@ +base_model = "google/gemini-3-pro-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2 +output = 12 +cache_read = 0.2 +cache_write = 4.5 + +[limit] +context = 1_048_576 diff --git a/providers/requesty/models/vertex/gemini-3-pro-preview.toml b/providers/requesty/models/vertex/gemini-3-pro-preview.toml new file mode 100644 index 00000000000..d26ff73e64b --- /dev/null +++ b/providers/requesty/models/vertex/gemini-3-pro-preview.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-3-pro-preview" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2 +output = 12 +cache_read = 0.2 +cache_write = 4.5 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-3.1-flash-image.toml b/providers/requesty/models/vertex/gemini-3.1-flash-image.toml new file mode 100644 index 00000000000..eac77d825ab --- /dev/null +++ b/providers/requesty/models/vertex/gemini-3.1-flash-image.toml @@ -0,0 +1,11 @@ +base_model = "google/gemini-3.1-flash-image" +tool_call = true +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.5 +output = 2 diff --git a/providers/requesty/models/vertex/gemini-3.1-flash-lite.toml b/providers/requesty/models/vertex/gemini-3.1-flash-lite.toml new file mode 100644 index 00000000000..e8e370dceca --- /dev/null +++ b/providers/requesty/models/vertex/gemini-3.1-flash-lite.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-3.1-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.25 +output = 1.5 +cache_read = 0.025 +cache_write = 0.08333 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-3.1-flash-lite@eu.toml b/providers/requesty/models/vertex/gemini-3.1-flash-lite@eu.toml new file mode 100644 index 00000000000..e8e370dceca --- /dev/null +++ b/providers/requesty/models/vertex/gemini-3.1-flash-lite@eu.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-3.1-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.25 +output = 1.5 +cache_read = 0.025 +cache_write = 0.08333 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-3.1-flash-lite@us.toml b/providers/requesty/models/vertex/gemini-3.1-flash-lite@us.toml new file mode 100644 index 00000000000..e8e370dceca --- /dev/null +++ b/providers/requesty/models/vertex/gemini-3.1-flash-lite@us.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-3.1-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.25 +output = 1.5 +cache_read = 0.025 +cache_write = 0.08333 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-3.1-pro-preview.toml b/providers/requesty/models/vertex/gemini-3.1-pro-preview.toml new file mode 100644 index 00000000000..a0e675e7dbc --- /dev/null +++ b/providers/requesty/models/vertex/gemini-3.1-pro-preview.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-3.1-pro-preview" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2 +output = 12 +cache_read = 0.2 +cache_write = 4.5 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-3.1-pro-preview:flex.toml b/providers/requesty/models/vertex/gemini-3.1-pro-preview:flex.toml new file mode 100644 index 00000000000..f56a8d5b6f5 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-3.1-pro-preview:flex.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-3.1-pro-preview" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1 +output = 6 +cache_read = 0.1 +cache_write = 2.75 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-3.5-flash-lite.toml b/providers/requesty/models/vertex/gemini-3.5-flash-lite.toml new file mode 100644 index 00000000000..591afd35a8f --- /dev/null +++ b/providers/requesty/models/vertex/gemini-3.5-flash-lite.toml @@ -0,0 +1,13 @@ +base_model = "google/gemini-3.5-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.03 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-3.5-flash-lite@eu.toml b/providers/requesty/models/vertex/gemini-3.5-flash-lite@eu.toml new file mode 100644 index 00000000000..591afd35a8f --- /dev/null +++ b/providers/requesty/models/vertex/gemini-3.5-flash-lite@eu.toml @@ -0,0 +1,13 @@ +base_model = "google/gemini-3.5-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.3 +output = 2.5 +cache_read = 0.03 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-3.5-flash.toml b/providers/requesty/models/vertex/gemini-3.5-flash.toml new file mode 100644 index 00000000000..e0e8bd261f6 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-3.5-flash.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-3.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.5 +output = 9 +cache_read = 0.15 +cache_write = 1.583 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-3.5-flash@eu.toml b/providers/requesty/models/vertex/gemini-3.5-flash@eu.toml new file mode 100644 index 00000000000..e0e8bd261f6 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-3.5-flash@eu.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-3.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.5 +output = 9 +cache_read = 0.15 +cache_write = 1.583 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-3.5-flash@us.toml b/providers/requesty/models/vertex/gemini-3.5-flash@us.toml new file mode 100644 index 00000000000..e0e8bd261f6 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-3.5-flash@us.toml @@ -0,0 +1,14 @@ +base_model = "google/gemini-3.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.5 +output = 9 +cache_read = 0.15 +cache_write = 1.583 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/vertex/gemini-3.6-flash.toml b/providers/requesty/models/vertex/gemini-3.6-flash.toml new file mode 100644 index 00000000000..fca672b1638 --- /dev/null +++ b/providers/requesty/models/vertex/gemini-3.6-flash.toml @@ -0,0 +1,13 @@ +base_model = "google/gemini-3.6-flash" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.5 +output = 7 +cache_read = 0.15 + +[limit] +output = 65_535 diff --git a/providers/requesty/models/xai/grok-4-fast.toml b/providers/requesty/models/xai/grok-4-fast.toml index 3ee68aa54fe..509a8fe1bb0 100644 --- a/providers/requesty/models/xai/grok-4-fast.toml +++ b/providers/requesty/models/xai/grok-4-fast.toml @@ -5,11 +5,12 @@ release_date = "2025-09-19" last_updated = "2025-09-19" attachment = true reasoning = true -reasoning_options = [] temperature = true tool_call = true +structured_output = true knowledge = "2025-01" open_weights = false +reasoning_options = [] [cost] input = 0.2 diff --git a/providers/requesty/models/xai/grok-4.3.toml b/providers/requesty/models/xai/grok-4.3.toml new file mode 100644 index 00000000000..34ca0b33272 --- /dev/null +++ b/providers/requesty/models/xai/grok-4.3.toml @@ -0,0 +1,11 @@ +base_model = "xai/grok-4.3" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.25 +output = 2.5 +cache_read = 0.2 +cache_write = 1.25 diff --git a/providers/requesty/models/xai/grok-4.5.toml b/providers/requesty/models/xai/grok-4.5.toml new file mode 100644 index 00000000000..8211209791e --- /dev/null +++ b/providers/requesty/models/xai/grok-4.5.toml @@ -0,0 +1,11 @@ +base_model = "xai/grok-4.5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 2 +output = 6 +cache_read = 0.5 +cache_write = 2 diff --git a/providers/requesty/models/xai/grok-4.toml b/providers/requesty/models/xai/grok-4.toml index 303ad59609d..5ac5cd6ca38 100644 --- a/providers/requesty/models/xai/grok-4.toml +++ b/providers/requesty/models/xai/grok-4.toml @@ -5,17 +5,18 @@ release_date = "2025-09-09" last_updated = "2025-09-09" attachment = true reasoning = true -reasoning_options = [] temperature = true tool_call = true +structured_output = true knowledge = "2025-01" open_weights = false +reasoning_options = [] [cost] -input = 3.00 -output = 15.00 +input = 3 +output = 15 cache_read = 0.75 -cache_write = 3.00 +cache_write = 3 [limit] context = 256_000 diff --git a/providers/requesty/models/xai/grok-build-0.1.toml b/providers/requesty/models/xai/grok-build-0.1.toml new file mode 100644 index 00000000000..b503e0bc7de --- /dev/null +++ b/providers/requesty/models/xai/grok-build-0.1.toml @@ -0,0 +1,10 @@ +base_model = "xai/grok-build-0.1" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1 +output = 2 +cache_read = 0.1 diff --git a/providers/requesty/models/xiaomi/mimo-v2.5-pro.toml b/providers/requesty/models/xiaomi/mimo-v2.5-pro.toml new file mode 100644 index 00000000000..aa48c4cec8b --- /dev/null +++ b/providers/requesty/models/xiaomi/mimo-v2.5-pro.toml @@ -0,0 +1,11 @@ +base_model = "xiaomi/mimo-v2.5-pro" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.435 +output = 0.87 +cache_read = 0.0036 diff --git a/providers/requesty/models/xiaomi/mimo-v2.5.toml b/providers/requesty/models/xiaomi/mimo-v2.5.toml new file mode 100644 index 00000000000..1e62e67be98 --- /dev/null +++ b/providers/requesty/models/xiaomi/mimo-v2.5.toml @@ -0,0 +1,11 @@ +base_model = "xiaomi/mimo-v2.5" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.14 +output = 0.28 +cache_read = 0.0028 diff --git a/providers/requesty/models/zai/GLM-4.5.toml b/providers/requesty/models/zai/GLM-4.5.toml new file mode 100644 index 00000000000..1bfc1dc37a4 --- /dev/null +++ b/providers/requesty/models/zai/GLM-4.5.toml @@ -0,0 +1,11 @@ +base_model = "zhipuai/glm-4.5" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.6 +output = 2.2 +cache_read = 0.11 diff --git a/providers/requesty/models/zai/GLM-4.6.toml b/providers/requesty/models/zai/GLM-4.6.toml new file mode 100644 index 00000000000..8ddc409830e --- /dev/null +++ b/providers/requesty/models/zai/GLM-4.6.toml @@ -0,0 +1,15 @@ +base_model = "zhipuai/glm-4.6" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.6 +output = 2.2 +cache_read = 0.11 + +[limit] +context = 200_000 +output = 128_000 diff --git a/providers/requesty/models/zai/GLM-4.7.toml b/providers/requesty/models/zai/GLM-4.7.toml new file mode 100644 index 00000000000..61f03d87b20 --- /dev/null +++ b/providers/requesty/models/zai/GLM-4.7.toml @@ -0,0 +1,15 @@ +base_model = "zhipuai/glm-4.7" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 0.6 +output = 2.2 +cache_read = 0.11 + +[limit] +context = 200_000 +output = 128_000 diff --git a/providers/requesty/models/zai/GLM-5.toml b/providers/requesty/models/zai/GLM-5.toml new file mode 100644 index 00000000000..10aff5e6e63 --- /dev/null +++ b/providers/requesty/models/zai/GLM-5.toml @@ -0,0 +1,15 @@ +base_model = "zhipuai/glm-5" +structured_output = false + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1 +output = 3.2 +cache_read = 0.2 + +[limit] +context = 200_000 +output = 128_000 diff --git a/providers/requesty/models/zai/glm-5.1.toml b/providers/requesty/models/zai/glm-5.1.toml new file mode 100644 index 00000000000..e00d95efab6 --- /dev/null +++ b/providers/requesty/models/zai/glm-5.1.toml @@ -0,0 +1,13 @@ +base_model = "zhipuai/glm-5.1" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.4 +output = 4.4 +cache_read = 0.26 + +[limit] +output = 128_000 diff --git a/providers/requesty/models/zai/glm-5.2.toml b/providers/requesty/models/zai/glm-5.2.toml new file mode 100644 index 00000000000..53fc6c72074 --- /dev/null +++ b/providers/requesty/models/zai/glm-5.2.toml @@ -0,0 +1,13 @@ +base_model = "zhipuai/glm-5.2" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "max"] + +[cost] +input = 1.4 +output = 4.4 +cache_read = 0.26 + +[limit] +output = 128_000