@mastra/core
Version:
Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.
1,503 lines (1,500 loc) • 328 kB
JavaScript
import { ModelsDevGateway, createOpenRouter } from './chunk-GVHEFJCD.js';
import { NetlifyGateway } from './chunk-RR3AHQZQ.js';
import { MastraModelGateway, createAnthropic, MASTRA_USER_AGENT, GATEWAY_AUTH_HEADER } from './chunk-NNMDHEQV.js';
import { MastraError } from './chunk-FJEVLHJT.js';
import fs from 'fs';
import { createRequire } from 'module';
import os from 'os';
import path from 'path';
// src/llm/model/gateways/mastra.ts
var MastraGateway = class extends MastraModelGateway {
constructor(config) {
super();
this.config = config;
}
config;
id = "mastra";
name = "Memory Gateway";
getBaseUrl() {
const raw = this.config?.baseUrl ?? process.env["MASTRA_GATEWAY_URL"] ?? "https://gateway-api.mastra.ai";
return raw.replace(/\/+$/, "").replace(/\/v1$/, "");
}
shouldEnable() {
return !!(this.config?.apiKey ?? process.env["MASTRA_GATEWAY_API_KEY"]);
}
async fetchProviders() {
if (!this.shouldEnable()) {
return {};
}
const openrouterConfig = PROVIDER_REGISTRY["openrouter"];
const models = openrouterConfig?.models ?? [];
const providers = {
mastra: {
apiKeyEnvVar: "MASTRA_GATEWAY_API_KEY",
apiKeyHeader: "Authorization",
name: "Memory Gateway",
gateway: "mastra",
models: [...models],
docUrl: "https://mastra.ai/docs/gateway"
}
};
return providers;
}
async buildUrl(_modelId) {
return `${this.getBaseUrl()}/v1`;
}
async getApiKey() {
const apiKey = this.config?.apiKey ?? process.env["MASTRA_GATEWAY_API_KEY"];
if (!apiKey) {
throw new MastraError({
id: "MASTRA_GATEWAY_NO_API_KEY",
domain: "LLM",
category: "UNKNOWN",
text: "Missing MASTRA_GATEWAY_API_KEY environment variable"
});
}
return apiKey;
}
resolveLanguageModel({
modelId,
providerId,
apiKey,
headers
}) {
const baseURL = `${this.getBaseUrl()}/v1`;
const fullModelId = `${providerId}/${modelId}`;
if (this.config?.customFetch && providerId === "anthropic") {
return createAnthropic({
apiKey: "oauth-gateway-placeholder",
baseURL,
headers: {
"User-Agent": MASTRA_USER_AGENT,
[GATEWAY_AUTH_HEADER]: `Bearer ${apiKey}`,
...headers
},
fetch: this.config.customFetch
})(modelId);
}
if (this.config?.customFetch) {
return createOpenRouter({
apiKey: "oauth-gateway-placeholder",
baseURL,
headers: {
"User-Agent": MASTRA_USER_AGENT,
[GATEWAY_AUTH_HEADER]: `Bearer ${apiKey}`,
...headers
},
fetch: this.config.customFetch
}).chat(fullModelId);
}
return createOpenRouter({
apiKey,
baseURL,
headers: {
"User-Agent": MASTRA_USER_AGENT,
...headers
}
}).chat(fullModelId);
}
};
// src/llm/model/provider-registry.json
var provider_registry_default = {
providers: {
helicone: {
url: "https://ai-gateway.helicone.ai/v1",
apiKeyEnvVar: "HELICONE_API_KEY",
apiKeyHeader: "Authorization",
name: "Helicone",
models: [
"chatgpt-4o-latest",
"claude-3-haiku-20240307",
"claude-3.5-haiku",
"claude-3.5-sonnet-v2",
"claude-3.7-sonnet",
"claude-4.5-haiku",
"claude-4.5-opus",
"claude-4.5-sonnet",
"claude-haiku-4-5-20251001",
"claude-opus-4",
"claude-opus-4-1",
"claude-opus-4-1-20250805",
"claude-sonnet-4",
"claude-sonnet-4-5-20250929",
"deepseek-r1-distill-llama-70b",
"deepseek-reasoner",
"deepseek-tng-r1t2-chimera",
"deepseek-v3",
"deepseek-v3.1-terminus",
"deepseek-v3.2",
"ernie-4.5-21b-a3b-thinking",
"gemini-2.5-flash",
"gemini-2.5-flash-lite",
"gemini-2.5-pro",
"gemini-3-pro-preview",
"gemma-3-12b-it",
"gemma2-9b-it",
"glm-4.6",
"gpt-4.1",
"gpt-4.1-mini",
"gpt-4.1-mini-2025-04-14",
"gpt-4.1-nano",
"gpt-4o",
"gpt-4o-mini",
"gpt-5",
"gpt-5-chat-latest",
"gpt-5-codex",
"gpt-5-mini",
"gpt-5-nano",
"gpt-5-pro",
"gpt-5.1",
"gpt-5.1-chat-latest",
"gpt-5.1-codex",
"gpt-5.1-codex-mini",
"gpt-oss-120b",
"gpt-oss-20b",
"grok-3",
"grok-3-mini",
"grok-4",
"grok-4-1-fast-non-reasoning",
"grok-4-1-fast-reasoning",
"grok-4-fast-non-reasoning",
"grok-4-fast-reasoning",
"grok-code-fast-1",
"hermes-2-pro-llama-3-8b",
"kimi-k2-0711",
"kimi-k2-0905",
"kimi-k2-thinking",
"llama-3.1-8b-instant",
"llama-3.1-8b-instruct",
"llama-3.1-8b-instruct-turbo",
"llama-3.3-70b-instruct",
"llama-3.3-70b-versatile",
"llama-4-maverick",
"llama-4-scout",
"llama-guard-4",
"llama-prompt-guard-2-22m",
"llama-prompt-guard-2-86m",
"mistral-large-2411",
"mistral-nemo",
"mistral-small",
"o1",
"o1-mini",
"o3",
"o3-mini",
"o3-pro",
"o4-mini",
"qwen2.5-coder-7b-fast",
"qwen3-235b-a22b-thinking",
"qwen3-30b-a3b",
"qwen3-32b",
"qwen3-coder",
"qwen3-coder-30b-a3b-instruct",
"qwen3-next-80b-a3b-instruct",
"qwen3-vl-235b-a22b-instruct",
"sonar",
"sonar-deep-research",
"sonar-pro",
"sonar-reasoning",
"sonar-reasoning-pro"
],
docUrl: "https://helicone.ai/models",
gateway: "models.dev"
},
auriko: {
url: "https://api.auriko.ai/v1",
apiKeyEnvVar: "AURIKO_API_KEY",
apiKeyHeader: "Authorization",
name: "Auriko",
models: [
"claude-opus-4-6",
"claude-opus-4-7",
"claude-sonnet-4-6",
"deepseek-v4-flash",
"deepseek-v4-pro",
"gemini-2.5-flash",
"gemini-2.5-pro",
"gemini-3.1-pro-preview",
"glm-5.1",
"grok-4.3",
"kimi-k2.5",
"kimi-k2.6",
"minimax-m2-7",
"minimax-m2-7-highspeed",
"qwen-3.6-plus"
],
docUrl: "https://docs.auriko.ai",
gateway: "models.dev"
},
firepass: {
url: "https://api.fireworks.ai/inference/v1/",
apiKeyEnvVar: "FIREPASS_API_KEY",
apiKeyHeader: "Authorization",
name: "Fireworks (Firepass)",
models: ["accounts/fireworks/routers/kimi-k2p6-turbo"],
docUrl: "https://docs.fireworks.ai/firepass",
gateway: "models.dev"
},
"nano-gpt": {
url: "https://nano-gpt.com/api/v1",
apiKeyEnvVar: "NANO_GPT_API_KEY",
apiKeyHeader: "Authorization",
name: "NanoGPT",
models: [
"Alibaba-NLP/Tongyi-DeepResearch-30B-A3B",
"Baichuan-M2",
"Baichuan4-Air",
"Baichuan4-Turbo",
"CrucibleLab/L3.3-70B-Loki-V2.0",
"Doctor-Shotgun/MS3.2-24B-Magnum-Diamond",
"EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0",
"EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1",
"EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2",
"EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2",
"Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B",
"Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B",
"GLM-4.5-Air-Derestricted",
"GLM-4.5-Air-Derestricted-Iceblink",
"GLM-4.5-Air-Derestricted-Iceblink-ReExtract",
"GLM-4.5-Air-Derestricted-Iceblink-v2",
"GLM-4.5-Air-Derestricted-Iceblink-v2-ReExtract",
"GLM-4.5-Air-Derestricted-Steam",
"GLM-4.5-Air-Derestricted-Steam-ReExtract",
"GLM-4.6-Derestricted-v5",
"GalrionSoftworks/MN-LooseCannon-12B-v1",
"Gemma-3-27B-ArliAI-RPMax-v3",
"Gemma-3-27B-Big-Tiger-v3",
"Gemma-3-27B-CardProjector-v4",
"Gemma-3-27B-Glitter",
"Gemma-3-27B-Nidum-Uncensored",
"Gemma-3-27B-it",
"Gemma-3-27B-it-Abliterated",
"Gryphe/MythoMax-L2-13b",
"Infermatic/MN-12B-Inferor-v0.0",
"KAT-Coder-Air-V1",
"KAT-Coder-Exp-72B-1010",
"KAT-Coder-Pro-V1",
"LLM360/K2-Think",
"LatitudeGames/Wayfarer-Large-70B-Llama-3.3",
"Llama-3.3+(3.1v3.3)-70B-Hanami-x1",
"Llama-3.3+(3.1v3.3)-70B-New-Dawn-v1.1",
"Llama-3.3+(3v3.3)-70B-TenyxChat-DaybreakStorywriter",
"Llama-3.3-70B-Anthrobomination",
"Llama-3.3-70B-Argunaut-1-SFT",
"Llama-3.3-70B-ArliAI-RPMax-v1.4",
"Llama-3.3-70B-ArliAI-RPMax-v2",
"Llama-3.3-70B-ArliAI-RPMax-v3",
"Llama-3.3-70B-Aurora-Borealis",
"Llama-3.3-70B-Bigger-Body",
"Llama-3.3-70B-Cirrus-x1",
"Llama-3.3-70B-Cu-Mai-R1",
"Llama-3.3-70B-Damascus-R1",
"Llama-3.3-70B-Dark-Ages-v0.1",
"Llama-3.3-70B-Electra-R1",
"Llama-3.3-70B-Electranova-v1.0",
"Llama-3.3-70B-Fallen-R1-v1",
"Llama-3.3-70B-Fallen-v1",
"Llama-3.3-70B-Forgotten-Abomination-v5.0",
"Llama-3.3-70B-Forgotten-Safeword-3.6",
"Llama-3.3-70B-GeneticLemonade-Opus",
"Llama-3.3-70B-GeneticLemonade-Unleashed-v3",
"Llama-3.3-70B-Ignition-v0.1",
"Llama-3.3-70B-Incandescent-Malevolence",
"Llama-3.3-70B-Legion-V2.1",
"Llama-3.3-70B-MS-Nevoria",
"Llama-3.3-70B-Magnum-v4-SE",
"Llama-3.3-70B-Magnum-v4-SE-Cirrus-x1-SLERP",
"Llama-3.3-70B-Mhnnn-x1",
"Llama-3.3-70B-MiraiFanfare",
"Llama-3.3-70B-Mokume-Gane-R1",
"Llama-3.3-70B-Nova",
"Llama-3.3-70B-Predatorial-Extasy",
"Llama-3.3-70B-Progenitor-V3.3",
"Llama-3.3-70B-RAWMAW",
"Llama-3.3-70B-Sapphira-0.1",
"Llama-3.3-70B-Sapphira-0.2",
"Llama-3.3-70B-Shakudo",
"Llama-3.3-70B-StrawberryLemonade-v1.0",
"Llama-3.3-70B-Strawberrylemonade-v1.2",
"Llama-3.3-70B-The-Omega-Directive-Unslop-v2.0",
"Llama-3.3-70B-The-Omega-Directive-Unslop-v2.1",
"Llama-3.3-70B-Vulpecula-R1",
"Magistral-Small-2506",
"MarinaraSpaghetti/NemoMix-Unleashed-12B",
"Meta-Llama-3-1-8B-Instruct-FP8",
"MiniMax-M1",
"MiniMax-M2",
"MiniMaxAI/MiniMax-M1-80k",
"Mistral-Nemo-12B-Instruct-2407",
"NeverSleep/Llama-3-Lumimaid-70B-v0.1",
"NeverSleep/Lumimaid-v0.2-70B",
"NousResearch 2/DeepHermes-3-Mistral-24B-Preview",
"NousResearch 2/Hermes-4-70B:thinking",
"NousResearch 2/hermes-3-llama-3.1-70b",
"NousResearch 2/hermes-4-405b",
"NousResearch 2/hermes-4-405b:thinking",
"NousResearch 2/hermes-4-70b",
"QwQ-32B-ArliAI-RpR-v1",
"Qwen2.5-32B-EVA-v0.2",
"ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0",
"ReadyArt/The-Omega-Abomination-L-70B-v1.0",
"Salesforce/Llama-xLAM-2-70b-fc-r",
"Sao10K/L3-8B-Stheno-v3.2",
"Sao10K/L3.1-70B-Euryale-v2.2",
"Sao10K/L3.1-70B-Hanami-x1",
"Sao10K/L3.3-70B-Euryale-v2.3",
"Steelskull/L3.3-Cu-Mai-R1-70b",
"Steelskull/L3.3-Electra-R1-70b",
"Steelskull/L3.3-MS-Evalebis-70b",
"Steelskull/L3.3-MS-Evayale-70B",
"Steelskull/L3.3-MS-Nevoria-70b",
"Steelskull/L3.3-Nevoria-R1-70b",
"TEE/deepseek-r1-0528",
"TEE/deepseek-v3.1",
"TEE/deepseek-v3.2",
"TEE/gemma-3-27b-it",
"TEE/glm-4.6",
"TEE/glm-4.7",
"TEE/glm-4.7-flash",
"TEE/glm-5",
"TEE/gpt-oss-120b",
"TEE/gpt-oss-20b",
"TEE/kimi-k2-thinking",
"TEE/kimi-k2.5",
"TEE/kimi-k2.5-thinking",
"TEE/llama3-3-70b",
"TEE/minimax-m2.1",
"TEE/qwen2.5-vl-72b-instruct",
"TEE/qwen3-30b-a3b-instruct-2507",
"TEE/qwen3-coder",
"TEE/qwen3.5-397b-a17b",
"THUDM/GLM-4-32B-0414",
"THUDM/GLM-4-9B-0414",
"THUDM/GLM-Z1-32B-0414",
"THUDM/GLM-Z1-9B-0414",
"THUDM/GLM-Z1-Rumination-32B-0414",
"TheDrummer 2/Anubis-70B-v1",
"TheDrummer 2/Anubis-70B-v1.1",
"TheDrummer 2/Cydonia-24B-v2",
"TheDrummer 2/Cydonia-24B-v4",
"TheDrummer 2/Cydonia-24B-v4.1",
"TheDrummer 2/Cydonia-24B-v4.3",
"TheDrummer 2/Magidonia-24B-v4.3",
"TheDrummer 2/Rocinante-12B-v1.1",
"TheDrummer 2/UnslopNemo-12B-v4.1",
"TheDrummer 2/skyfall-36b-v2",
"Tongyi-Zhiwen/QwenLong-L1-32B",
"VongolaChouko/Starcannon-Unleashed-12B-v1.0",
"abacusai/Dracarys-72B-Instruct",
"aion-labs/aion-1.0",
"aion-labs/aion-1.0-mini",
"aion-labs/aion-rp-llama-3.1-8b",
"alibaba/qwen3.6-flash",
"allenai/molmo-2-8b",
"allenai/olmo-3-32b-think",
"allenai/olmo-3.1-32b-instruct",
"allenai/olmo-3.1-32b-think",
"amazon/nova-2-lite-v1",
"amazon/nova-lite-v1",
"amazon/nova-micro-v1",
"amazon/nova-pro-v1",
"anthracite-org/magnum-v2-72b",
"anthracite-org/magnum-v4-72b",
"anthropic/claude-opus-4.6",
"anthropic/claude-opus-4.6:thinking",
"anthropic/claude-opus-4.6:thinking:low",
"anthropic/claude-opus-4.6:thinking:max",
"anthropic/claude-opus-4.6:thinking:medium",
"anthropic/claude-sonnet-4.6",
"anthropic/claude-sonnet-4.6:thinking",
"arcee-ai/trinity-large",
"arcee-ai/trinity-mini",
"asi1-mini",
"auto-model",
"auto-model-basic",
"auto-model-premium",
"auto-model-standard",
"azure-gpt-4-turbo",
"azure-gpt-4o",
"azure-gpt-4o-mini",
"azure-o1",
"azure-o3-mini",
"baidu/ernie-4.5-300b-a47b",
"baidu/ernie-4.5-vl-28b-a3b",
"baseten/Kimi-K2-Instruct-FP4",
"brave",
"brave-pro",
"brave-research",
"chroma",
"chutesai/Mistral-Small-3.2-24B-Instruct-2506",
"claude-3-5-haiku-20241022",
"claude-3-5-sonnet-20240620",
"claude-3-5-sonnet-20241022",
"claude-3-7-sonnet-20250219",
"claude-3-7-sonnet-reasoner",
"claude-3-7-sonnet-thinking",
"claude-3-7-sonnet-thinking:1024",
"claude-3-7-sonnet-thinking:128000",
"claude-3-7-sonnet-thinking:32768",
"claude-3-7-sonnet-thinking:8192",
"claude-haiku-4-5-20251001",
"claude-opus-4-1-20250805",
"claude-opus-4-1-thinking",
"claude-opus-4-1-thinking:1024",
"claude-opus-4-1-thinking:32000",
"claude-opus-4-1-thinking:32768",
"claude-opus-4-1-thinking:8192",
"claude-opus-4-20250514",
"claude-opus-4-5-20251101",
"claude-opus-4-5-20251101:thinking",
"claude-opus-4-thinking",
"claude-opus-4-thinking:1024",
"claude-opus-4-thinking:32000",
"claude-opus-4-thinking:32768",
"claude-opus-4-thinking:8192",
"claude-sonnet-4-20250514",
"claude-sonnet-4-5-20250929",
"claude-sonnet-4-5-20250929-thinking",
"claude-sonnet-4-thinking",
"claude-sonnet-4-thinking:1024",
"claude-sonnet-4-thinking:32768",
"claude-sonnet-4-thinking:64000",
"claude-sonnet-4-thinking:8192",
"cognitivecomputations/dolphin-2.9.2-qwen2-72b",
"cohere/command-r",
"cohere/command-r-plus-08-2024",
"command-a-reasoning-08-2025",
"deepclaude",
"deepcogito/cogito-v1-preview-qwen-32B",
"deepcogito/cogito-v2.1-671b",
"deepseek-ai/DeepSeek-R1-0528",
"deepseek-ai/DeepSeek-V3.1",
"deepseek-ai/DeepSeek-V3.1-Terminus",
"deepseek-ai/DeepSeek-V3.1-Terminus:thinking",
"deepseek-ai/DeepSeek-V3.1:thinking",
"deepseek-ai/deepseek-v3.2-exp",
"deepseek-ai/deepseek-v3.2-exp-thinking",
"deepseek-chat",
"deepseek-chat-cheaper",
"deepseek-math-v2",
"deepseek-r1",
"deepseek-r1-sambanova",
"deepseek-reasoner",
"deepseek-reasoner-cheaper",
"deepseek-v3-0324",
"deepseek/deepseek-prover-v2-671b",
"deepseek/deepseek-v3.2",
"deepseek/deepseek-v3.2-speciale",
"deepseek/deepseek-v3.2:thinking",
"dmind/dmind-1",
"dmind/dmind-1-mini",
"doubao-1-5-thinking-pro-250415",
"doubao-1-5-thinking-pro-vision-250415",
"doubao-1-5-thinking-vision-pro-250428",
"doubao-1.5-pro-256k",
"doubao-1.5-pro-32k",
"doubao-1.5-vision-pro-32k",
"doubao-seed-1-6-250615",
"doubao-seed-1-6-flash-250615",
"doubao-seed-1-6-thinking-250615",
"doubao-seed-1-8-251215",
"doubao-seed-2-0-code-preview-260215",
"doubao-seed-2-0-lite-260215",
"doubao-seed-2-0-mini-260215",
"doubao-seed-2-0-pro-260215",
"doubao-seed-code-preview-latest",
"ernie-4.5-8k-preview",
"ernie-4.5-turbo-128k",
"ernie-4.5-turbo-vl-32k",
"ernie-5.0-thinking-latest",
"ernie-5.0-thinking-preview",
"ernie-x1-32k",
"ernie-x1-32k-preview",
"ernie-x1-turbo-32k",
"ernie-x1.1-preview",
"essentialai/rnj-1-instruct",
"exa-answer",
"exa-research",
"exa-research-pro",
"failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5",
"fastgpt",
"featherless-ai/Qwerky-72B",
"gemini-2.0-flash-001",
"gemini-2.0-flash-exp-image-generation",
"gemini-2.0-flash-lite",
"gemini-2.0-flash-thinking-exp-01-21",
"gemini-2.0-flash-thinking-exp-1219",
"gemini-2.0-pro-exp-02-05",
"gemini-2.0-pro-reasoner",
"gemini-2.5-flash",
"gemini-2.5-flash-lite",
"gemini-2.5-flash-lite-preview-06-17",
"gemini-2.5-flash-lite-preview-09-2025",
"gemini-2.5-flash-lite-preview-09-2025-thinking",
"gemini-2.5-flash-nothinking",
"gemini-2.5-flash-preview-04-17",
"gemini-2.5-flash-preview-04-17:thinking",
"gemini-2.5-flash-preview-05-20",
"gemini-2.5-flash-preview-05-20:thinking",
"gemini-2.5-flash-preview-09-2025",
"gemini-2.5-flash-preview-09-2025-thinking",
"gemini-2.5-pro",
"gemini-2.5-pro-exp-03-25",
"gemini-2.5-pro-preview-03-25",
"gemini-2.5-pro-preview-05-06",
"gemini-2.5-pro-preview-06-05",
"gemini-3-pro-image-preview",
"gemini-3-pro-preview",
"gemini-3-pro-preview-thinking",
"gemini-exp-1206",
"glm-4",
"glm-4-air",
"glm-4-air-0111",
"glm-4-airx",
"glm-4-flash",
"glm-4-long",
"glm-4-plus",
"glm-4-plus-0111",
"glm-4.1v-thinking-flash",
"glm-4.1v-thinking-flashx",
"glm-z1-air",
"glm-z1-airx",
"glm-zero-preview",
"google/gemini-3-flash-preview",
"google/gemini-3-flash-preview-thinking",
"google/gemini-flash-1.5",
"grok-3-beta",
"grok-3-fast-beta",
"grok-3-mini-beta",
"grok-3-mini-fast-beta",
"hidream",
"huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated",
"huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated",
"huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated",
"huihui-ai/Llama-3.3-70B-Instruct-abliterated",
"huihui-ai/Qwen2.5-32B-Instruct-abliterated",
"hunyuan-t1-latest",
"hunyuan-turbos-20250226",
"inflatebot/MN-12B-Mag-Mell-R1",
"inflection/inflection-3-pi",
"inflection/inflection-3-productivity",
"jamba-large",
"jamba-large-1.6",
"jamba-large-1.7",
"jamba-mini",
"jamba-mini-1.6",
"jamba-mini-1.7",
"kimi-k2-instruct-fast",
"kimi-thinking-preview",
"learnlm-1.5-pro-experimental",
"meganova-ai/manta-flash-1.0",
"meganova-ai/manta-mini-1.0",
"meganova-ai/manta-pro-1.0",
"meituan-longcat/LongCat-Flash-Chat-FP8",
"meta-llama/llama-3.1-8b-instruct",
"meta-llama/llama-3.2-3b-instruct",
"meta-llama/llama-3.2-90b-vision-instruct",
"meta-llama/llama-3.3-70b-instruct",
"meta-llama/llama-4-maverick",
"meta-llama/llama-4-scout",
"microsoft/MAI-DS-R1-FP8",
"microsoft/wizardlm-2-8x22b",
"minimax/minimax-01",
"minimax/minimax-m2-her",
"minimax/minimax-m2.1",
"minimax/minimax-m2.5",
"minimax/minimax-m2.7",
"miromind-ai/mirothinker-v1.5-235b",
"mistral-small-31-24b-instruct",
"mistralai/Devstral-Small-2505",
"mistralai/Mistral-Nemo-Instruct-2407",
"mistralai/codestral-2508",
"mistralai/devstral-2-123b-instruct-2512",
"mistralai/ministral-14b-2512",
"mistralai/ministral-14b-instruct-2512",
"mistralai/ministral-3b-2512",
"mistralai/ministral-8b-2512",
"mistralai/mistral-7b-instruct",
"mistralai/mistral-large",
"mistralai/mistral-large-3-675b-instruct-2512",
"mistralai/mistral-medium-3",
"mistralai/mistral-medium-3.1",
"mistralai/mistral-saba",
"mistralai/mistral-small-creative",
"mistralai/mistral-tiny",
"mistralai/mixtral-8x22b-instruct-v0.1",
"mistralai/mixtral-8x7b-instruct-v0.1",
"mlabonne/NeuralDaredevil-8B-abliterated",
"moonshotai/Kimi-Dev-72B",
"moonshotai/Kimi-K2-Instruct-0905",
"moonshotai/kimi-k2-instruct",
"moonshotai/kimi-k2-instruct-0711",
"moonshotai/kimi-k2-thinking",
"moonshotai/kimi-k2-thinking-original",
"moonshotai/kimi-k2-thinking-turbo-original",
"moonshotai/kimi-k2.5",
"moonshotai/kimi-k2.5:thinking",
"moonshotai/kimi-k2.6",
"moonshotai/kimi-k2.6:thinking",
"nex-agi/deepseek-v3.1-nex-n1",
"nothingiisreal/L3.1-70B-Celeste-V0.1-BF16",
"nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
"nvidia/Llama-3.1-Nemotron-Ultra-253B-v1",
"nvidia/Llama-3.3-Nemotron-Super-49B-v1",
"nvidia/Llama-3_3-Nemotron-Super-49B-v1_5",
"nvidia/nemotron-3-nano-30b-a3b",
"nvidia/nvidia-nemotron-nano-9b-v2",
"openai/chatgpt-4o-latest",
"openai/gpt-3.5-turbo",
"openai/gpt-4-turbo",
"openai/gpt-4-turbo-preview",
"openai/gpt-4.1",
"openai/gpt-4.1-mini",
"openai/gpt-4.1-nano",
"openai/gpt-4o",
"openai/gpt-4o-2024-08-06",
"openai/gpt-4o-2024-11-20",
"openai/gpt-4o-mini",
"openai/gpt-4o-mini-search-preview",
"openai/gpt-4o-search-preview",
"openai/gpt-5",
"openai/gpt-5-chat-latest",
"openai/gpt-5-codex",
"openai/gpt-5-mini",
"openai/gpt-5-nano",
"openai/gpt-5-pro",
"openai/gpt-5.1",
"openai/gpt-5.1-2025-11-13",
"openai/gpt-5.1-chat",
"openai/gpt-5.1-chat-latest",
"openai/gpt-5.1-codex",
"openai/gpt-5.1-codex-max",
"openai/gpt-5.1-codex-mini",
"openai/gpt-5.2",
"openai/gpt-5.2-chat",
"openai/gpt-5.2-codex",
"openai/gpt-5.2-pro",
"openai/gpt-oss-120b",
"openai/gpt-oss-20b",
"openai/gpt-oss-safeguard-20b",
"openai/o1",
"openai/o1-preview",
"openai/o1-pro",
"openai/o3",
"openai/o3-deep-research",
"openai/o3-mini",
"openai/o3-mini-high",
"openai/o3-mini-low",
"openai/o3-pro-2025-06-10",
"openai/o4-mini",
"openai/o4-mini-deep-research",
"openai/o4-mini-high",
"pamanseau/OpenReasoning-Nemotron-32B",
"phi-4-mini-instruct",
"phi-4-multimodal-instruct",
"qvq-max",
"qwen-3.6-plus",
"qwen-image",
"qwen-long",
"qwen-max",
"qwen-plus",
"qwen-turbo",
"qwen/Qwen3.6-35B-A3B",
"qwen/Qwen3.6-35B-A3B:thinking",
"qwen/qwen3.5-397b-a17b",
"qwen25-vl-72b-instruct",
"qwen3-30b-a3b-instruct-2507",
"qwen3-coder-30b-a3b-instruct",
"qwen3-max-2026-01-23",
"qwen3-vl-235b-a22b-instruct-original",
"qwen3-vl-235b-a22b-thinking",
"qwen3.6-max-preview",
"qwq-32b",
"raifle/sorcererlm-8x22b",
"sarvan-medium",
"shisa-ai/shisa-v2-llama3.3-70b",
"shisa-ai/shisa-v2.1-llama3.3-70b",
"sonar",
"sonar-deep-research",
"sonar-pro",
"sonar-reasoning-pro",
"soob3123/GrayLine-Qwen3-8B",
"soob3123/Veiled-Calla-12B",
"soob3123/amoral-gemma3-27B-v2",
"step-2-16k-exp",
"step-2-mini",
"step-3",
"step-r1-v-mini",
"stepfun-ai/step-3.5-flash",
"stepfun-ai/step-3.5-flash:thinking",
"study_gpt-chatgpt-4o-latest",
"tencent/Hunyuan-MT-7B",
"tngtech/DeepSeek-TNG-R1T2-Chimera",
"tngtech/tng-r1t-chimera",
"undi95/remm-slerp-l2-13b",
"universal-summarizer",
"unsloth/gemma-3-12b-it",
"unsloth/gemma-3-1b-it",
"unsloth/gemma-3-27b-it",
"unsloth/gemma-3-4b-it",
"v0-1.0-md",
"v0-1.5-lg",
"v0-1.5-md",
"venice-uncensored",
"venice-uncensored:web",
"x-ai/grok-4-07-09",
"x-ai/grok-4-fast",
"x-ai/grok-4-fast:thinking",
"x-ai/grok-4.1-fast",
"x-ai/grok-4.1-fast-reasoning",
"x-ai/grok-code-fast-1",
"xiaomi/mimo-v2-flash",
"xiaomi/mimo-v2-flash-original",
"xiaomi/mimo-v2-flash-thinking",
"xiaomi/mimo-v2-flash-thinking-original",
"yi-large",
"yi-lightning",
"yi-medium-200k",
"z-ai/glm-4.5v",
"z-ai/glm-4.5v:thinking",
"z-ai/glm-4.6",
"z-ai/glm-4.6:thinking",
"z-image-turbo",
"zai-org/glm-4.7",
"zai-org/glm-4.7-flash",
"zai-org/glm-5",
"zai-org/glm-5.1",
"zai-org/glm-5.1:thinking",
"zai-org/glm-5:thinking"
],
docUrl: "https://docs.nano-gpt.com",
gateway: "models.dev"
},
"io-net": {
url: "https://api.intelligence.io.solutions/api/v1",
apiKeyEnvVar: "IOINTELLIGENCE_API_KEY",
apiKeyHeader: "Authorization",
name: "IO.NET",
models: [
"Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar",
"Qwen/Qwen2.5-VL-32B-Instruct",
"Qwen/Qwen3-235B-A22B-Thinking-2507",
"Qwen/Qwen3-Next-80B-A3B-Instruct",
"deepseek-ai/DeepSeek-R1-0528",
"meta-llama/Llama-3.2-90B-Vision-Instruct",
"meta-llama/Llama-3.3-70B-Instruct",
"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"mistralai/Devstral-Small-2505",
"mistralai/Magistral-Small-2506",
"mistralai/Mistral-Large-Instruct-2411",
"mistralai/Mistral-Nemo-Instruct-2407",
"moonshotai/Kimi-K2-Instruct-0905",
"moonshotai/Kimi-K2-Thinking",
"openai/gpt-oss-120b",
"openai/gpt-oss-20b",
"zai-org/GLM-4.6"
],
docUrl: "https://io.net/docs/guides/intelligence/io-intelligence",
gateway: "models.dev"
},
inception: {
url: "https://api.inceptionlabs.ai/v1/",
apiKeyEnvVar: "INCEPTION_API_KEY",
apiKeyHeader: "Authorization",
name: "Inception",
models: ["mercury-2", "mercury-edit-2"],
docUrl: "https://platform.inceptionlabs.ai/docs",
gateway: "models.dev"
},
submodel: {
url: "https://llm.submodel.ai/v1",
apiKeyEnvVar: "SUBMODEL_INSTAGEN_ACCESS_KEY",
apiKeyHeader: "Authorization",
name: "submodel",
models: [
"Qwen/Qwen3-235B-A22B-Instruct-2507",
"Qwen/Qwen3-235B-A22B-Thinking-2507",
"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
"deepseek-ai/DeepSeek-R1-0528",
"deepseek-ai/DeepSeek-V3-0324",
"deepseek-ai/DeepSeek-V3.1",
"openai/gpt-oss-120b",
"zai-org/GLM-4.5-Air",
"zai-org/GLM-4.5-FP8"
],
docUrl: "https://submodel.gitbook.io",
gateway: "models.dev"
},
requesty: {
url: "https://router.requesty.ai/v1",
apiKeyEnvVar: "REQUESTY_API_KEY",
apiKeyHeader: "Authorization",
name: "Requesty",
models: [
"anthropic/claude-3-7-sonnet",
"anthropic/claude-haiku-4-5",
"anthropic/claude-opus-4",
"anthropic/claude-opus-4-1",
"anthropic/claude-opus-4-5",
"anthropic/claude-opus-4-6",
"anthropic/claude-sonnet-4",
"anthropic/claude-sonnet-4-5",
"anthropic/claude-sonnet-4-6",
"google/gemini-2.5-flash",
"google/gemini-2.5-pro",
"google/gemini-3-flash-preview",
"google/gemini-3-pro-preview",
"openai/gpt-4.1",
"openai/gpt-4.1-mini",
"openai/gpt-4o-mini",
"openai/gpt-5",
"openai/gpt-5-chat",
"openai/gpt-5-codex",
"openai/gpt-5-image",
"openai/gpt-5-mini",
"openai/gpt-5-nano",
"openai/gpt-5-pro",
"openai/gpt-5.1",
"openai/gpt-5.1-chat",
"openai/gpt-5.1-codex",
"openai/gpt-5.1-codex-max",
"openai/gpt-5.1-codex-mini",
"openai/gpt-5.2",
"openai/gpt-5.2-chat",
"openai/gpt-5.2-codex",
"openai/gpt-5.2-pro",
"openai/gpt-5.3-codex",
"openai/gpt-5.4",
"openai/gpt-5.4-pro",
"openai/o4-mini",
"xai/grok-4",
"xai/grok-4-fast"
],
docUrl: "https://requesty.ai/solution/llm-routing/models",
gateway: "models.dev"
},
zai: {
url: "https://api.z.ai/api/paas/v4",
apiKeyEnvVar: "ZHIPU_API_KEY",
apiKeyHeader: "Authorization",
name: "Z.AI",
models: [
"glm-4.5",
"glm-4.5-air",
"glm-4.5-flash",
"glm-4.5v",
"glm-4.6",
"glm-4.6v",
"glm-4.7",
"glm-4.7-flash",
"glm-4.7-flashx",
"glm-5",
"glm-5-turbo",
"glm-5.1",
"glm-5v-turbo"
],
docUrl: "https://docs.z.ai/guides/overview/pricing",
gateway: "models.dev"
},
"zai-coding-plan": {
url: "https://api.z.ai/api/coding/paas/v4",
apiKeyEnvVar: "ZHIPU_API_KEY",
apiKeyHeader: "Authorization",
name: "Z.AI Coding Plan",
models: ["glm-4.5-air", "glm-4.7", "glm-5-turbo", "glm-5.1", "glm-5v-turbo"],
docUrl: "https://docs.z.ai/devpack/overview",
gateway: "models.dev"
},
deepinfra: {
apiKeyEnvVar: "DEEPINFRA_API_KEY",
name: "Deep Infra",
models: [
"MiniMaxAI/MiniMax-M2",
"MiniMaxAI/MiniMax-M2.1",
"MiniMaxAI/MiniMax-M2.5",
"Qwen/Qwen3-Coder-480B-A35B-Instruct",
"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo",
"Qwen/Qwen3.5-35B-A3B",
"Qwen/Qwen3.5-397B-A17B",
"Qwen/Qwen3.6-35B-A3B",
"anthropic/claude-3-7-sonnet-latest",
"anthropic/claude-4-opus",
"deepseek-ai/DeepSeek-R1-0528",
"deepseek-ai/DeepSeek-V3.2",
"deepseek-ai/DeepSeek-V4-Flash",
"deepseek-ai/DeepSeek-V4-Pro",
"google/gemma-4-26B-A4B-it",
"google/gemma-4-31B-it",
"meta-llama/Llama-3.1-70B-Instruct",
"meta-llama/Llama-3.1-70B-Instruct-Turbo",
"meta-llama/Llama-3.1-8B-Instruct",
"meta-llama/Llama-3.1-8B-Instruct-Turbo",
"meta-llama/Llama-3.3-70B-Instruct-Turbo",
"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"meta-llama/Llama-4-Scout-17B-16E-Instruct",
"moonshotai/Kimi-K2-Instruct",
"moonshotai/Kimi-K2-Instruct-0905",
"moonshotai/Kimi-K2-Thinking",
"moonshotai/Kimi-K2.5",
"moonshotai/Kimi-K2.6",
"openai/gpt-oss-120b",
"openai/gpt-oss-20b",
"xiaomi/mimo-v2.5",
"xiaomi/mimo-v2.5-pro",
"zai-org/GLM-4.6",
"zai-org/GLM-4.6V",
"zai-org/GLM-4.7",
"zai-org/GLM-4.7-Flash",
"zai-org/GLM-5",
"zai-org/GLM-5.1"
],
docUrl: "https://deepinfra.com/models",
gateway: "models.dev",
npm: "@ai-sdk/deepinfra"
},
clarifai: {
url: "https://api.clarifai.com/v2/ext/openai/v1",
apiKeyEnvVar: "CLARIFAI_PAT",
apiKeyHeader: "Authorization",
name: "Clarifai",
models: [
"arcee_ai/AFM/models/trinity-mini",
"clarifai/main/models/mm-poly-8b",
"deepseek-ai/deepseek-ocr/models/DeepSeek-OCR",
"minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput",
"mistralai/completion/models/Ministral-3-14B-Reasoning-2512",
"mistralai/completion/models/Ministral-3-3B-Reasoning-2512",
"moonshotai/chat-completion/models/Kimi-K2_6",
"openai/chat-completion/models/gpt-oss-120b-high-throughput",
"openai/chat-completion/models/gpt-oss-20b",
"qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct",
"qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507",
"qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507"
],
docUrl: "https://docs.clarifai.com/compute/inference/",
gateway: "models.dev"
},
moark: {
url: "https://moark.com/v1",
apiKeyEnvVar: "MOARK_API_KEY",
apiKeyHeader: "Authorization",
name: "Moark",
models: ["GLM-4.7", "MiniMax-M2.1"],
docUrl: "https://moark.com/docs/openapi/v1#tag/%E6%96%87%E6%9C%AC%E7%94%9F%E6%88%90",
gateway: "models.dev"
},
frogbot: {
url: "https://app.frogbot.ai/api/v1",
apiKeyEnvVar: "FROGBOT_API_KEY",
apiKeyHeader: "Authorization",
name: "FrogBot",
models: [
"claude-haiku-4-5",
"claude-opus-4-6",
"claude-opus-4-7",
"claude-sonnet-4-6",
"deepseek-v4-pro",
"gemini-2.5-flash",
"gemini-2.5-pro",
"gemini-3-1-pro-preview",
"gemini-3-flash-preview",
"gpt-4o",
"gpt-5-3-codex",
"gpt-5-4-mini",
"gpt-5-4-nano",
"gpt-5-5",
"gpt-oss-120b",
"gpt-oss-20b",
"grok-4-1-fast-non-reasoning",
"grok-4-1-fast-reasoning",
"grok-4-3",
"grok-code-fast-1",
"kimi-k2-6",
"kimi-k2.5",
"minimax-m2-5",
"minimax-m2-7",
"qwen-3-6-plus",
"zai-glm-5-1"
],
docUrl: "https://docs.frogbot.ai",
gateway: "models.dev"
},
wandb: {
url: "https://api.inference.wandb.ai/v1",
apiKeyEnvVar: "WANDB_API_KEY",
apiKeyHeader: "Authorization",
name: "Weights & Biases",
models: [
"MiniMaxAI/MiniMax-M2.5",
"OpenPipe/Qwen3-14B-Instruct",
"Qwen/Qwen3-235B-A22B-Instruct-2507",
"Qwen/Qwen3-235B-A22B-Thinking-2507",
"Qwen/Qwen3-30B-A3B-Instruct-2507",
"Qwen/Qwen3-Coder-480B-A35B-Instruct",
"deepseek-ai/DeepSeek-V3.1",
"meta-llama/Llama-3.1-70B-Instruct",
"meta-llama/Llama-3.1-8B-Instruct",
"meta-llama/Llama-3.3-70B-Instruct",
"meta-llama/Llama-4-Scout-17B-16E-Instruct",
"microsoft/Phi-4-mini-instruct",
"moonshotai/Kimi-K2.5",
"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8",
"openai/gpt-oss-120b",
"openai/gpt-oss-20b",
"zai-org/GLM-5-FP8",
"zai-org/GLM-5.1"
],
docUrl: "https://docs.wandb.ai/guides/integrations/inference/",
gateway: "models.dev"
},
gmicloud: {
url: "https://api.gmi-serving.com/v1",
apiKeyEnvVar: "GMICLOUD_API_KEY",
apiKeyHeader: "Authorization",
name: "GMI Cloud",
models: [
"anthropic/claude-opus-4.6",
"anthropic/claude-opus-4.7",
"anthropic/claude-sonnet-4.6",
"deepseek-ai/DeepSeek-V4-Flash",
"deepseek-ai/DeepSeek-V4-Pro",
"moonshotai/Kimi-K2.6",
"zai-org/GLM-5-FP8",
"zai-org/GLM-5.1-FP8"
],
docUrl: "https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference",
gateway: "models.dev"
},
ambient: {
url: "https://api.ambient.xyz/v1",
apiKeyEnvVar: "AMBIENT_API_KEY",
apiKeyHeader: "Authorization",
name: "Ambient",
models: ["moonshotai/kimi-k2.6", "zai-org/GLM-5.1-FP8"],
docUrl: "https://ambient.xyz",
gateway: "models.dev"
},
"routing-run": {
url: "https://api.routing.run/v1",
apiKeyEnvVar: "ROUTING_RUN_API_KEY",
apiKeyHeader: "Authorization",
name: "routing.run",
models: [
"route/deepseek-v3.2",
"route/deepseek-v4-flash",
"route/deepseek-v4-flash-6bit",
"route/deepseek-v4-pro",
"route/deepseek-v4-pro-6bit",
"route/gemma-4-31b-it",
"route/glm-5.1",
"route/glm-5.1-6bit",
"route/kimi-k2.5",
"route/kimi-k2.6",
"route/kimi-k2.6-6bit",
"route/mimo-v2.5-pro",
"route/mimo-v2.5-pro-6bit",
"route/minimax-m2.5",
"route/minimax-m2.5-highspeed",
"route/minimax-m2.7",
"route/minimax-m2.7-highspeed",
"route/mistral-large-3",
"route/mistral-medium-2505",
"route/mistral-small-2503",
"route/qwen3.6-27b",
"route/step-3.5-flash",
"route/step-3.5-flash-2603",
"route/stepfun-3.5-flash"
],
docUrl: "https://docs.routing.run/api-reference/models",
gateway: "models.dev"
},
"the-grid-ai": {
url: "https://api.thegrid.ai/v1",
apiKeyEnvVar: "THEGRIDAI_API_KEY",
apiKeyHeader: "Authorization",
name: "The Grid AI",
models: [
"agent-max",
"agent-prime",
"agent-standard",
"code-max",
"code-prime",
"code-standard",
"text-max",
"text-prime",
"text-standard"
],
docUrl: "https://thegrid.ai/docs",
gateway: "models.dev"
},
fastrouter: {
url: "https://go.fastrouter.ai/api/v1",
apiKeyEnvVar: "FASTROUTER_API_KEY",
apiKeyHeader: "Authorization",
name: "FastRouter",
models: [
"anthropic/claude-opus-4.1",
"anthropic/claude-sonnet-4",
"deepseek-ai/deepseek-r1-distill-llama-70b",
"google/gemini-2.5-flash",
"google/gemini-2.5-pro",
"moonshotai/kimi-k2",
"openai/gpt-4.1",
"openai/gpt-5",
"openai/gpt-5-mini",
"openai/gpt-5-nano",
"openai/gpt-oss-120b",
"openai/gpt-oss-20b",
"qwen/qwen3-coder",
"x-ai/grok-4",
"z-ai/glm-5"
],
docUrl: "https://fastrouter.ai/models",
gateway: "models.dev"
},
"tencent-coding-plan": {
url: "https://api.lkeap.cloud.tencent.com/coding/v3",
apiKeyEnvVar: "TENCENT_CODING_PLAN_API_KEY",
apiKeyHeader: "Authorization",
name: "Tencent Coding Plan (China)",
models: [
"glm-5",
"hunyuan-2.0-instruct",
"hunyuan-2.0-thinking",
"hunyuan-t1",
"hunyuan-turbos",
"kimi-k2.5",
"minimax-m2.5",
"tc-code-latest"
],
docUrl: "https://cloud.tencent.com/document/product/1772/128947",
gateway: "models.dev"
},
cortecs: {
url: "https://api.cortecs.ai/v1",
apiKeyEnvVar: "CORTECS_API_KEY",
apiKeyHeader: "Authorization",
name: "Cortecs",
models: [
"claude-4-5-sonnet",
"claude-4-6-sonnet",
"claude-haiku-4-5",
"claude-opus4-5",
"claude-opus4-6",
"claude-opus4-7",
"claude-sonnet-4",
"codestral-2508",
"deepseek-r1-0528",
"deepseek-v3-0324",
"deepseek-v3.2",
"deepseek-v4-flash",
"deepseek-v4-pro",
"devstral-2512",
"devstral-small-2512",
"gemini-2.5-pro",
"glm-4.5",
"glm-4.5-air",
"glm-4.7",
"glm-4.7-flash",
"glm-5",
"glm-5.1",
"gpt-4.1",
"gpt-oss-120b",
"hermes-4-70b",
"intellect-3",
"kimi-k2-instruct",
"kimi-k2-thinking",
"kimi-k2.5",
"kimi-k2.6",
"llama-3.1-405b-instruct",
"llama-3.3-70b-instruct",
"minimax-m2",
"minimax-m2.1",
"minimax-m2.5",
"minimax-m2.7",
"mistral-large-2512",
"mixtral-8x7B-instruct-v0.1",
"nemotron-3-super-120b-a12b",
"nova-pro-v1",
"qwen-2.5-72b-instruct",
"qwen3-235b-a22b-instruct-2507",
"qwen3-32b",
"qwen3-coder-30b-a3b-instruct",
"qwen3-coder-480b-a35b-instruct",
"qwen3-coder-next",
"qwen3-next-80b-a3b-thinking",
"qwen3.5-122b-a10b",
"qwen3.5-397b-a17b"
],
docUrl: "https://api.cortecs.ai/v1/models",
gateway: "models.dev"
},
baseten: {
url: "https://inference.baseten.co/v1",
apiKeyEnvVar: "BASETEN_API_KEY",
apiKeyHeader: "Authorization",
name: "Baseten",
models: [
"MiniMaxAI/MiniMax-M2.5",
"deepseek-ai/DeepSeek-V3-0324",
"deepseek-ai/DeepSeek-V3.1",
"deepseek-ai/DeepSeek-V4-Pro",
"moonshotai/Kimi-K2.5",
"moonshotai/Kimi-K2.6",
"nvidia/Nemotron-120B-A12B",
"openai/gpt-oss-120b",
"zai-org/GLM-4.6",
"zai-org/GLM-4.7",
"zai-org/GLM-5"
],
docUrl: "https://docs.baseten.co/development/model-apis/overview",
gateway: "models.dev"
},
llama: {
url: "https://api.llama.com/compat/v1/",
apiKeyEnvVar: "LLAMA_API_KEY",
apiKeyHeader: "Authorization",
name: "Llama",
models: [
"cerebras-llama-4-maverick-17b-128e-instruct",
"cerebras-llama-4-scout-17b-16e-instruct",
"groq-llama-4-maverick-17b-128e-instruct",
"llama-3.3-70b-instruct",
"llama-3.3-8b-instruct",
"llama-4-maverick-17b-128e-instruct-fp8",
"llama-4-scout-17b-16e-instruct-fp8"
],
docUrl: "https://llama.developer.meta.com/docs/models",
gateway: "models.dev"
},
"novita-ai": {
url: "https://api.novita.ai/openai",
apiKeyEnvVar: "NOVITA_API_KEY",
apiKeyHeader: "Authorization",
name: "NovitaAI",
models: [
"baichuan/baichuan-m2-32b",
"baidu/ernie-4.5-21B-a3b",
"baidu/ernie-4.5-21B-a3b-thinking",
"baidu/ernie-4.5-300b-a47b-paddle",
"baidu/ernie-4.5-vl-28b-a3b",
"baidu/ernie-4.5-vl-28b-a3b-thinking",
"baidu/ernie-4.5-vl-424b-a47b",
"deepseek/deepseek-ocr",
"deepseek/deepseek-ocr-2",
"deepseek/deepseek-prover-v2-671b",
"deepseek/deepseek-r1-0528",
"deepseek/deepseek-r1-0528-qwen3-8b",
"deepseek/deepseek-r1-distill-llama-70b",
"deepseek/deepseek-r1-distill-qwen-14b",
"deepseek/deepseek-r1-distill-qwen-32b",
"deepseek/deepseek-r1-turbo",
"deepseek/deepseek-v3-0324",
"deepseek/deepseek-v3-turbo",
"deepseek/deepseek-v3.1",
"deepseek/deepseek-v3.1-terminus",
"deepseek/deepseek-v3.2",
"deepseek/deepseek-v3.2-exp",
"deepseek/deepseek-v4-flash",
"deepseek/deepseek-v4-pro",
"google/gemma-3-12b-it",
"google/gemma-3-27b-it",
"google/gemma-4-26b-a4b-it",
"google/gemma-4-31b-it",
"gryphe/mythomax-l2-13b",
"inclusionai/ling-2.6-1t",
"inclusionai/ling-2.6-flash",
"kwaipilot/kat-coder-pro",
"meta-llama/llama-3-70b-instruct",
"meta-llama/llama-3-8b-instruct",
"meta-llama/llama-3.1-8b-instruct",
"meta-llama/llama-3.2-3b-instruct",
"meta-llama/llama-3.3-70b-instruct",
"meta-llama/llama-4-maverick-17b-128e-instruct-fp8",
"meta-llama/llama-4-scout-17b-16e-instruct",
"microsoft/wizardlm-2-8x22b",
"minimax/minimax-m2",
"minimax/minimax-m2.1",
"minimax/minimax-m2.5",
"minimax/minimax-m2.5-highspeed",
"minimax/minimax-m2.7",
"minimaxai/minimax-m1-80k",
"mistralai/mistral-nemo",
"moonshotai/kimi-k2-0905",
"moonshotai/kimi-k2-instruct",
"moonshotai/kimi-k2-thinking",
"moonshotai/kimi-k2.5",
"moonshotai/kimi-k2.6",
"nousresearch/hermes-2-pro-llama-3-8b",
"openai/gpt-oss-120b",
"openai/gpt-oss-20b",
"paddlepaddle/paddleocr-vl",
"qwen/qwen-2.5-72b-instruct",
"qwen/qwen-mt-plus",
"qwen/qwen2.5-7b-instruct",
"qwen/qwen2.5-vl-72b-instruct",
"qwen/qwen3-235b-a22b-fp8",
"qwen/qwen3-235b-a22b-instruct-2507",
"qwen/qwen3-235b-a22b-thinking-2507",
"qwen/qwen3-30b-a3b-fp8",
"qwen/qwen3-32b-fp8",
"qwen/qwen3-4b-fp8",
"qwen/qwen3-8b-fp8",
"qwen/qwen3-coder-30b-a3b-instruct",
"qwen/qwen3-coder-480b-a35b-instruct",
"qwen/qwen3-coder-next",
"qwen/qwen3-max",
"qwen/qwen3-next-80b-a3b-instruct",
"qwen/qwen3-next-80b-a3b-thinking",
"qwen/qwen3-omni-30b-a3b-instruct",
"qwen/qwen3-omni-30b-a3b-thinking",
"qwen/qwen3-vl-235b-a22b-instruct",
"qwen/qwen3-vl-235b-a22b-thinking",
"qwen/qwen3-vl-30b-a3b-instruct",
"qwen/qwen3-vl-30b-a3b-thinking",
"qwen/qwen3-vl-8b-instruct",
"qwen/qwen3.5-122b-a10b",
"qwen/qwen3.5-27b",
"qwen/qwen3.5-35b-a3b",
"qwen/qwen3.5-397b-a17b",
"sao10K/L3-8B-stheno-v3.2",
"sao10K/l3-70b-euryale-v2.1",
"sao10K/l3-8b-lunaris",
"sao10K/l31-70b-euryale-v2.2",
"xiaomimimo/mimo-v2-flash",
"zai-org/autoglm-phone-9b-multilingual",
"zai-org/glm-4.5",
"zai-org/glm-4.5-air",
"zai-org/glm-4.5v",
"zai-org/glm-4.6",
"zai-org/glm-4.6v",
"zai-org/glm-4.7",
"zai-org/glm-4.7-flash",
"zai-org/glm-5",
"zai-org/glm-5.1"
],
docUrl: "https://novita.ai/docs/guides/introduction",
gateway: "models.dev"
},
digitalocean: {
url: "https://inference.do-ai.run/v1",
apiKeyEnvVar: "DIGITALOCEAN_ACCESS_TOKEN",
apiKeyHeader: "Authorization",
name: "DigitalOcean",
models: [
"alibaba-qwen3-32b",
"all-mini-lm-l6-v2",
"anthropic-claude-4.1-opus",
"anthropic-claude-4.5-haiku",
"anthropic-claude-4.5-sonnet",
"anthropic-claude-4.6-sonnet",
"anthropic-claude-haiku-4.5",
"anthropic-claude-opus-4",
"anthropic-claude-opus-4.5",
"anthropic-claude-opus-4.6",
"anthropic-claude-opus-4.7",
"anthropic-claude-sonnet-4",
"arcee-trinity-large-thinking",
"bge-m3",
"bge-reranker-v2-m3",
"deepseek-3.2",
"deepseek-r1-distill-llama-70b",
"deepseek-v3",
"deepseek-v4-pro",
"e5-large-v2",
"fal-ai/elevenlabs/tts/multilingual-v2",
"fal-ai/fast-sdxl",
"fal-ai/flux/schnell",
"fal-ai/stable-audio-25/text-to-audio",
"gemma-4-31B-it",
"glm-5",
"gte-large-en-v1.5",
"kimi-k2.5",
"kimi-k2.6",
"llama-4-maverick",
"llama3-8b-instruct",
"llama3.3-70b-instruct",
"minimax-m2.5",
"ministral-3-8b-instruct-2512",
"mistral-3-14B",
"mistral-7b-instruct-v0.3",
"multi-qa-mpnet-base-dot-v1",
"nemotron-3-nano-30b",
"nemotron-3-nano-omni",
"nemotron-nano-12b-v2-vl",
"nvidia-nemotron-3-super-120b",
"openai-gpt-4.1",
"openai-gpt-4o",
"openai-gpt-4o-mini",
"openai-gpt-5",
"openai-gpt-5-mini",
"openai-gpt-5-nano",
"openai-gpt-5.1-codex-max",
"openai-gpt-5.2",
"openai-gpt-5.2-pro",
"openai-gpt-5.3-codex",
"openai-gpt-5.4",
"openai-gpt-5.4-mini",
"openai-gpt-5.4-nano",
"openai-gpt-5.4-pro",
"openai-gpt-5.5",
"openai-gpt-image-1",
"openai-gpt-image-1.5",
"openai-gpt-image-2",
"openai-gpt-oss-120b",
"openai-gpt-oss-20b",
"openai-o1",
"openai-o3",
"openai-o3-mini",
"qwen-2.5-14b-instruct",
"qwen3-coder-flash",
"qwen3-embedding-0.6b",
"qwen3-tts-voicedesign",
"qwen3.5-397b-a17b",
"stable-diffusion-3.5-large",
"wan2-2-t2v-a14b"
],
docUrl: "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/",
gateway: "models.dev"
},
moonshotai: {
url: "https://api.moonshot.ai/anthropic/v1",
apiKeyEnvVar: "MOONSHOT_API_KEY",
apiKeyHeader: "Authorization",
name: "Moonshot AI",
models: [
"kimi-k2-0711-preview",
"kimi-k2-0905-preview",
"kimi-k2-thinking",
"kimi-k2-thinking-turbo",
"kimi-k2-turbo-preview",
"kimi-k2.5",
"kimi-k2.6"
],
docUrl: "https://platform.moonshot.ai/docs/api/chat",
gateway: "models.dev",
npm: "@ai-sdk/anthropic"
},
mistral: {
url: "https://api.mistral.ai/v1",
apiKeyEnvVar: "MISTRAL_API_KEY",
name: "Mistral",
models: [
"codestral-latest",
"devstral-2512",
"devstral-medium-2507",
"devstral-medium-latest",
"devstral-small-2505",
"devstral-small-2507",
"labs-devstral-small-2512",
"magistral-medium-latest",
"magistral-small",
"ministral-3b-latest",
"ministral-8b-latest",
"mistral-embed",
"mistral-large-2411",
"mistral-large-2512",
"mistral-large-latest",
"mistral-medium-2505",
"mistral-medium-2508",
"mistral-medium-2604",
"mistral-medium-latest",