Pular para o conteúdo principal

​
Synthetic

A Synthetic expõe endpoints compatíveis com Anthropic. O OpenClaw a registra como o provedor synthetic e usa a API Anthropic Messages.

​
Setup rápido

  1. Defina SYNTHETIC_API_KEY (ou execute o assistente abaixo).
  2. Execute o onboarding:
openclaw onboard --auth-choice synthetic-api-key
O modelo padrão é definido como: 
synthetic/hf:MiniMaxAI/MiniMax-M2.5

​
Exemplo de configuração

{
  env: { SYNTHETIC_API_KEY: "sk-..." },
  agents: {
    defaults: {
      model: { primary: "synthetic/hf:MiniMaxAI/MiniMax-M2.5" },
      models: { "synthetic/hf:MiniMaxAI/MiniMax-M2.5": { alias: "MiniMax M2.5" } },
    },
  },
  models: {
    mode: "merge",
    providers: {
      synthetic: {
        baseUrl: "https://api.synthetic.new/anthropic",
        apiKey: "${SYNTHETIC_API_KEY}",
        api: "anthropic-messages",
        models: [
          {
            id: "hf:MiniMaxAI/MiniMax-M2.5",
            name: "MiniMax M2.5",
            reasoning: false,
            input: ["text"],
            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
            contextWindow: 192000,
            maxTokens: 65536,
          },
        ],
      },
    },
  },
}
Observação: o cliente Anthropic do OpenClaw acrescenta /v1 à base URL, então use https://api.synthetic.new/anthropic (não /anthropic/v1). Se a Synthetic alterar sua base URL, substitua models.providers.synthetic.baseUrl.

​
Catálogo de modelos

Todos os modelos abaixo usam custo 0 (entrada/saída/cache).
ID do modeloJanela de contextoMáx. de tokensReasoningEntrada
hf:MiniMaxAI/MiniMax-M2.519200065536falsetext
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:moonshotai/Kimi-K2.52560008192truetext + image
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-Instruct2500008192falsetext + image
hf:zai-org/GLM-4.5128000128000falsetext
hf:zai-org/GLM-4.6198000128000falsetext
hf:zai-org/GLM-5256000128000truetext + image
hf:deepseek-ai/DeepSeek-V31280008192falsetext
hf:Qwen/Qwen3-235B-A22B-Thinking-25072560008192truetext

​
Observações

  • As referências de modelo usam synthetic/<modelId>.
  • Se você habilitar uma allowlist de modelos (agents.defaults.models), adicione todos os modelos que pretende usar.
  • Veja Provedores de modelo para as regras de provedores.