Asosiy tarkibga o'tish

​
49. Model provayderlari

  1. Bu sahifa LLM/model provayderlarini qamrab oladi (WhatsApp/Telegram kabi chat kanallari emas).
  2. Modelni tanlash qoidalari uchun qarang: /concepts/models.

​
2. Tezkor qoidalar

    1. Model havolalari provider/model formatidan foydalanadi (misol: opencode/claude-opus-4-6).
    1. Agar agents.defaults.models ni o‘rnatsangiz, u ruxsat etilgan ro‘yxatga (allowlist) aylanadi.
    1. CLI yordamchilari: openclaw onboard, openclaw models list, openclaw models set <provider/model>.

​
6. Ichki provayderlar (pi‑ai katalogi)

  1. OpenClaw pi‑ai katalogi bilan birga yetkazib beriladi. 8. Ushbu provayderlar hech qanday models.providers konfiguratsiyasini talab qilmaydi; faqat autentifikatsiyani sozlab, modelni tanlang.

​
9. OpenAI

    1. Provayder: openai
    1. Autentifikatsiya: OPENAI_API_KEY
    1. Namuna model: openai/gpt-5.1-codex
  • CLI: openclaw onboard --auth-choice openai-api-key
14. {
  agents: { defaults: { model: { primary: "openai/gpt-5.1-codex" } } },
}

​
15. Anthropic

    1. Provayder: anthropic
    1. Autentifikatsiya: ANTHROPIC_API_KEY yoki claude setup-token
    1. Namuna model: anthropic/claude-opus-4-6
    1. CLI: openclaw onboard --auth-choice token (setup-tokenni joylashtiring) yoki openclaw models auth paste-token --provider anthropic
20. {
  agents: { defaults: { model: { primary: "anthropic/claude-opus-4-6" } } },
}

​
21. OpenAI Code (Codex)

    1. Provayder: openai-codex
    1. Autentifikatsiya: OAuth (ChatGPT)
    1. Namuna model: openai-codex/gpt-5.3-codex
    1. CLI: openclaw onboard --auth-choice openai-codex yoki openclaw models auth login --provider openai-codex
26. {
  agents: { defaults: { model: { primary: "openai-codex/gpt-5.3-codex" } } },
}

​
27. OpenCode Zen

    1. Provayder: opencode
    1. Autentifikatsiya: OPENCODE_API_KEY (yoki OPENCODE_ZEN_API_KEY)
    1. Namuna model: opencode/claude-opus-4-6
  • CLI: openclaw onboard --auth-choice opencode-zen
32. {
  agents: { defaults: { model: { primary: "opencode/claude-opus-4-6" } } },
}

​
33. Google Gemini (API kalit)

    1. Provayder: google
    1. Autentifikatsiya: GEMINI_API_KEY
    1. Namuna model: google/gemini-3-pro-preview
  • CLI: openclaw onboard --auth-choice gemini-api-key

​
38. Google Vertex, Antigravity va Gemini CLI

    1. Provayderlar: google-vertex, google-antigravity, google-gemini-cli
    1. Autentifikatsiya: Vertex gcloud ADC’dan foydalanadi; Antigravity/Gemini CLI esa o‘ziga xos autentifikatsiya jarayonlaridan foydalanadi
    1. Antigravity OAuth biriktirilgan plagin sifatida yetkazib beriladi (google-antigravity-auth, sukut bo‘yicha o‘chirilgan).
      1. Yoqish: openclaw plugins enable google-antigravity-auth
      1. Kirish: openclaw models auth login --provider google-antigravity --set-default
    1. Gemini CLI OAuth biriktirilgan plagin sifatida yetkazib beriladi (google-gemini-cli-auth, sukut bo‘yicha o‘chirilgan).
      1. Yoqish: openclaw plugins enable google-gemini-cli-auth
      1. Kirish: openclaw models auth login --provider google-gemini-cli --set-default
      1. Eslatma: openclaw.json ichiga mijoz identifikatori (client id) yoki maxfiy kalitni (secret) kiritmaysiz. 48. CLI orqali kirish jarayoni tokenlarni shlyuz xostidagi autentifikatsiya profillarida saqlaydi.

​
49. Z.AI (GLM)

    1. Provayder: zai
    1. Avtorizatsiya: ZAI_API_KEY
    1. Namunaviy model: zai/glm-4.7
  • CLI: openclaw onboard --auth-choice zai-api-key
    • 4. Aliaslar: z.ai/* va z-ai/* zai/* ga normallashtiriladi

​
5. Vercel AI Gateway

    1. Provayder: vercel-ai-gateway
    1. Avtorizatsiya: AI_GATEWAY_API_KEY
    1. Namunaviy model: vercel-ai-gateway/anthropic/claude-opus-4.6
  • CLI: openclaw onboard --auth-choice ai-gateway-api-key

​
10. Boshqa ichki (built-in) provayderlar

  • OpenRouter: openrouter (OPENROUTER_API_KEY)
    1. Namunaviy model: openrouter/anthropic/claude-sonnet-4-5
  • xAI: xai (XAI_API_KEY)
  • Groq: groq (GROQ_API_KEY)
  • Cerebras: cerebras (CEREBRAS_API_KEY)
    • 16. Cerebras’dagi GLM modellari zai-glm-4.7 va zai-glm-4.6 identifikatorlaridan foydalanadi.
      1. OpenAI-mos asosiy URL: https://api.cerebras.ai/v1.
  • Mistral: mistral (MISTRAL_API_KEY)
  • GitHub Copilot: github-copilot (COPILOT_GITHUB_TOKEN / GH_TOKEN / GITHUB_TOKEN)
  • Hugging Face Inference: huggingface (HUGGINGFACE_HUB_TOKEN yoki HF_TOKEN) — OpenAI-compatible router; namuna model: huggingface/deepseek-ai/DeepSeek-R1; CLI: openclaw onboard --auth-choice huggingface-api-key. Qarang Hugging Face (Inference).

​
20. models.providers orqali provayderlar (custom/base URL)

  1. Maxsus provayderlarni yoki OpenAI/Anthropic‑mos proksilarni qo‘shish uchun models.providers (yoki models.json) dan foydalaning.

​
22. Moonshot AI (Kimi)

  1. Moonshot OpenAI-mos endpointlardan foydalanadi, shuning uchun uni maxsus provayder sifatida sozlang:
    1. Provayder: moonshot
    1. Avtorizatsiya: MOONSHOT_API_KEY
    1. Namunaviy model: moonshot/kimi-k2.5
  1. Kimi K2 model IDlari:
  • moonshot/kimi-k2.5
  • moonshot/kimi-k2-0905-preview
  • moonshot/kimi-k2-turbo-preview
  • moonshot/kimi-k2-thinking
    1. moonshot/kimi-k2-thinking-turbo
34. {
  agents: {
    defaults: { model: { primary: "moonshot/kimi-k2.5" } },
  },
  models: {
    mode: "merge",
    providers: {
      moonshot: {
        baseUrl: "https://api.moonshot.ai/v1",
        apiKey: "${MOONSHOT_API_KEY}",
        api: "openai-completions",
        models: [{ id: "kimi-k2.5", name: "Kimi K2.5" }],
      },
    },
  },
}

​
35. Kimi Coding

  1. Kimi Coding Moonshot AI’ning Anthropic-mos endpointidan foydalanadi:
    1. Provayder: kimi-coding
    1. Avtorizatsiya: KIMI_API_KEY
    1. Namunaviy model: kimi-coding/k2p5
40. {
  env: { KIMI_API_KEY: "sk-..." },
  agents: {
    defaults: { model: { primary: "kimi-coding/k2p5" } },
  },
}

​
41. Qwen OAuth (bepul daraja)

  1. Qwen Qwen Coder + Vision uchun qurilma-kod (device-code) oqimi orqali OAuth kirishni taqdim etadi.
  2. Biriktirilgan plaginini yoqing, so‘ng tizimga kiring:
44. openclaw plugins enable qwen-portal-auth
openclaw models auth login --provider qwen-portal --set-default
  1. Model havolalari:
  • qwen-portal/coder-model
  • qwen-portal/vision-model
  1. Sozlash tafsilotlari va eslatmalar uchun /providers/qwen ga qarang.

​
49. Synthetic

  1. Synthetic synthetic provayderi ortida Anthropic-mos modellalarni taqdim etadi:
  • Provider: synthetic
  • Auth: SYNTHETIC_API_KEY
  • Example model: synthetic/hf:MiniMaxAI/MiniMax-M2.1
  • CLI: openclaw onboard --auth-choice synthetic-api-key
{
  agents: {
    defaults: { model: { primary: "synthetic/hf:MiniMaxAI/MiniMax-M2.1" } },
  },
  models: {
    mode: "merge",
    providers: {
      synthetic: {
        baseUrl: "https://api.synthetic.new/anthropic",
        apiKey: "${SYNTHETIC_API_KEY}",
        api: "anthropic-messages",
        models: [{ id: "hf:MiniMaxAI/MiniMax-M2.1", name: "MiniMax M2.1" }],
      },
    },
  },
}

​
MiniMax

MiniMax is configured via models.providers because it uses custom endpoints:
  • MiniMax (Anthropic‑compatible): --auth-choice minimax-api
  • Auth: MINIMAX_API_KEY
See /providers/minimax for setup details, model options, and config snippets.

​
Ollama

Ollama is a local LLM runtime that provides an OpenAI-compatible API:
  • Provider: ollama
  • Auth: None required (local server)
  • Example model: ollama/llama3.3
  • Installation: https://ollama.ai
# Install Ollama, then pull a model:
ollama pull llama3.3

{
  agents: {
    defaults: { model: { primary: "ollama/llama3.3" } },
  },
}
Ollama is automatically detected when running locally at http://127.0.0.1:11434/v1. See /providers/ollama for model recommendations and custom configuration.

​
vLLM

vLLM — mahalliy (yoki self-hosted) OpenAI-compatible server:
  • Provider: vllm
  • Auth: Ixtiyoriy (serveringizga bog‘liq)
  • Standart base URL: http://127.0.0.1:8000/v1
Mahalliy auto-discovery’ni yoqish uchun (agar serveringiz auth talab qilmasa, istalgan qiymat mos keladi): 
export VLLM_API_KEY="vllm-local"
So‘ng modelni sozlang (/v1/models tomonidan qaytarilgan IDlardan birini qo‘llang): 
{
  agents: {
    defaults: { model: { primary: "vllm/your-model-id" } },
  },
}
Batafsil ma’lumot uchun qarang /providers/vllm.

​
Local proxies (LM Studio, vLLM, LiteLLM, etc.)

Example (OpenAI‑compatible): 
{
  agents: {
    defaults: {
      model: { primary: "lmstudio/minimax-m2.1-gs32" },
      models: { "lmstudio/minimax-m2.1-gs32": { alias: "Minimax" } },
    },
  },
  models: {
    providers: {
      lmstudio: {
        baseUrl: "http://localhost:1234/v1",
        apiKey: "LMSTUDIO_KEY",
        api: "openai-completions",
        models: [
          {
            id: "minimax-m2.1-gs32",
            name: "MiniMax M2.1",
            reasoning: false,
            input: ["text"],
            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
            contextWindow: 200000,
            maxTokens: 8192,
          },
        ],
      },
    },
  },
}
Notes:
  • For custom providers, reasoning, input, cost, contextWindow, and maxTokens are optional. When omitted, OpenClaw defaults to:
    • reasoning: false
    • input: ["text"]
    • cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }
    • contextWindow: 200000
    • maxTokens: 8192
  • Recommended: set explicit values that match your proxy/model limits.

​
CLI examples

openclaw onboard --auth-choice opencode-zen
openclaw models set opencode/claude-opus-4-6
openclaw models list
See also: /gateway/configuration for full configuration examples.