Asosiy tarkibga o'tish

​
Synthetic

Synthetic Anthropic’ga mos endpointlarni taqdim etadi. OpenClaw uni synthetic provayderi sifatida ro‘yxatdan o‘tkazadi va Anthropic Messages API’dan foydalanadi.

​
Tezkor sozlash

  1. SYNTHETIC_API_KEY ni o‘rnating (yoki quyidagi ustani ishga tushiring).
  2. Onboarding’ni ishga tushiring:
openclaw onboard --auth-choice synthetic-api-key
Standart model quyidagiga o‘rnatiladi: 
synthetic/hf:MiniMaxAI/MiniMax-M2.1

​
Konfiguratsiya namunasi

{
  env: { SYNTHETIC_API_KEY: "sk-..." },
  agents: {
    defaults: {
      model: { primary: "synthetic/hf:MiniMaxAI/MiniMax-M2.1" },
      models: { "synthetic/hf:MiniMaxAI/MiniMax-M2.1": { alias: "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",
            reasoning: false,
            input: ["text"],
            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
            contextWindow: 192000,
            maxTokens: 65536,
          },
        ],
      },
    },
  },
}
Eslatma: OpenClaw’ning Anthropic mijozi bazaviy URL’ga /v1 qo‘shadi, shuning uchun https://api.synthetic.new/anthropic dan foydalaning (/anthropic/v1 emas). Agar Synthetic bazaviy URL’ni o‘zgartirsa, models.providers.synthetic.baseUrl ni o‘zgartiring.

​
Model katalogi

Quyidagi barcha modellar 0 xarajatdan foydalanadi (kirish/chiqish/kesh).
Model IDKontekst oynasiMaksimal tokenlarMulohaza yuritishKirish
hf:MiniMaxAI/MiniMax-M2.119200065536falsetext
hf:moonshotai/Kimi-K2-Thinking2560008192truetext
hf:zai-org/GLM-4.7198000128000falsetext
hf:deepseek-ai/DeepSeek-R1-05281280008192falsetext
hf:deepseek-ai/DeepSeek-V3-03241280008192falsetext
hf:deepseek-ai/DeepSeek-V3.11280008192falsetext
hf:deepseek-ai/DeepSeek-V3.1-Terminus1280008192falsetext
hf:deepseek-ai/DeepSeek-V3.21590008192falsetext
hf:meta-llama/Llama-3.3-70B-Instruct1280008192falsetext
hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP85240008192falsetext
hf:moonshotai/Kimi-K2-Instruct-09052560008192falsetext
hf:openai/gpt-oss-120b1280008192falsetext
hf:Qwen/Qwen3-235B-A22B-Instruct-25072560008192falsetext
hf:Qwen/Qwen3-Coder-480B-A35B-Instruct2560008192falsetext
hf:Qwen/Qwen3-VL-235B-A22B-Instruct2500008192falsematn + rasm
hf:zai-org/GLM-4.5128000128000falsetext
hf:zai-org/GLM-4.6198000128000falsetext
hf:deepseek-ai/DeepSeek-V31280008192falsetext
hf:Qwen/Qwen3-235B-A22B-Thinking-25072560008192truetext

​
Notes

  • Model refs use synthetic/<modelId>.
  • If you enable a model allowlist (agents.defaults.models), add every model you plan to use.
  • See Model providers for provider rules.