Skip to main content
Synthetic exposes Anthropic-compatible endpoints. OpenClaw bundles it as the synthetic provider and uses the Anthropic Messages API.
PropertyValue
Providersynthetic
AuthSYNTHETIC_API_KEY
APIAnthropic Messages
Base URLhttps://api.synthetic.new/anthropic

​
Getting started

1

Get an API key

Get a SYNTHETIC_API_KEY from your Synthetic account, or let onboarding prompt you for one.
2

Run onboarding

openclaw onboard --auth-choice synthetic-api-key
3

Verify the default model

Onboarding sets the default model to:
synthetic/hf:MiniMaxAI/MiniMax-M2.5
OpenClaw’s Anthropic client appends /v1 to the base URL automatically, so use https://api.synthetic.new/anthropic (not /anthropic/v1). If Synthetic changes its base URL, override models.providers.synthetic.baseUrl.

​
Config example

{
  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,
          },
        ],
      },
    },
  },
}

​
Built-in catalog

All Synthetic models use cost 0 (input/output/cache).
Model IDContext windowMax tokensReasoningInput
hf:MiniMaxAI/MiniMax-M2.5192,00065,536notext
hf:moonshotai/Kimi-K2-Thinking256,0008,192yestext
hf:zai-org/GLM-4.7198,000128,000notext
hf:deepseek-ai/DeepSeek-R1-0528128,0008,192notext
hf:deepseek-ai/DeepSeek-V3-0324128,0008,192notext
hf:deepseek-ai/DeepSeek-V3.1128,0008,192notext
hf:deepseek-ai/DeepSeek-V3.1-Terminus128,0008,192notext
hf:deepseek-ai/DeepSeek-V3.2159,0008,192notext
hf:meta-llama/Llama-3.3-70B-Instruct128,0008,192notext
hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8524,0008,192notext
hf:moonshotai/Kimi-K2-Instruct-0905256,0008,192notext
hf:moonshotai/Kimi-K2.5256,0008,192yestext + image
hf:openai/gpt-oss-120b128,0008,192notext
hf:Qwen/Qwen3-235B-A22B-Instruct-2507256,0008,192notext
hf:Qwen/Qwen3-Coder-480B-A35B-Instruct256,0008,192notext
hf:Qwen/Qwen3-VL-235B-A22B-Instruct250,0008,192notext + image
hf:zai-org/GLM-4.5128,000128,000notext
hf:zai-org/GLM-4.6198,000128,000notext
hf:zai-org/GLM-5256,000128,000yestext + image
hf:deepseek-ai/DeepSeek-V3128,0008,192notext
hf:Qwen/Qwen3-235B-A22B-Thinking-2507256,0008,192yestext
Model refs use the form synthetic/<modelId>. Use openclaw models list --provider synthetic to see all models available on your account.
If you enable a model allowlist (agents.defaults.models), add every Synthetic model you plan to use. Models not in the allowlist are hidden from the agent.
If Synthetic changes its API endpoint, override the base URL:
{
  models: {
    providers: {
      synthetic: {
        baseUrl: "https://new-api.synthetic.new/anthropic",
      },
    },
  },
}
OpenClaw still appends /v1 automatically.

Model providers

Provider rules, model refs, and failover behavior.

Configuration reference

Full config schema including provider settings.

Synthetic

Synthetic dashboard and API docs.