How the integration works

OpenClaw accepts custom providers in its models configuration. Add DeepSeek-V4.io, reference the API key through an environment variable, and make DeepSeek V4 Flash the default agent model.

Before you start

• OpenClaw installed
• A paid DeepSeek-V4.io account with an API key from /developer
• Access to ~/.openclaw/openclaw.json

Configure OpenClaw

{
  "models": {
    "providers": {
      "deepseek-v4-io": {
        "baseUrl": "https://deepseek-v4.io/api/v1",
        "apiKey": "${DEEPSEEK_V4_API_KEY}",
        "api": "openai-completions",
        "models": [
          {
            "id": "deepseek-v4-flash",
            "name": "DeepSeek V4 Flash",
            "reasoning": true,
            "input": ["text"],
            "contextWindow": 1048576,
            "maxTokens": 65536
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "deepseek-v4-io/deepseek-v4-flash"
      }
    }
  }
}

export DEEPSEEK_V4_API_KEY="your-deepseek-v4-io-key"
openclaw

Verify the setup

The page remains Experimental until these checks pass against the public DeepSeek-V4.io gateway.

1. 1Confirm the default model resolves to deepseek-v4-io/deepseek-v4-flash.
2. 2Run an agent task that requires one safe tool call.
3. 3Confirm streaming continues after the tool result is returned.

Troubleshooting