Use OpenClaw

OpenClaw can register an OpenAI-compatible provider in ~/.openclaw/openclaw.json. No plugin is required.

1. Install OpenClaw

curl -fsSL --proto '=https' --tlsv1.2 https://openclaw.ai/install.sh | bash

Or install from npm and run onboarding yourself:

npm install -g openclaw@latest
openclaw onboard

See the OpenClaw install guide.

2. Create a Stream key

Generate an API key in the Stream console. It is shown once.

export CAMEL_API_KEY="qaml_live_..."

The gateway must see the same environment variable. If you run OpenClaw as a daemon, put the key in that service environment or in ~/.openclaw/.env if your install supports it.

3. Add the provider

Merge this into ~/.openclaw/openclaw.json. Keep any providers you already have. The file is JSON5, so comments and unquoted keys are allowed.

{
  models: {
    providers: {
      "camel-stream": {
        baseUrl: "https://stream.camelai.com/v1",
        apiKey: "${CAMEL_API_KEY}",
        api: "openai-completions",
        models: [
          {
            id: "deepseek-v4-flash",
            name: "DeepSeek V4 Flash",
            reasoning: true,
            input: ["text"],
            contextWindow: 262144,
            maxTokens: 32768,
            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }
          }
        ]
      }
    }
  },
  agents: {
    defaults: {
      model: {
        primary: "camel-stream/deepseek-v4-flash"
      }
    }
  }
}

api: "openai-completions" is the transport for Stream's /v1/chat/completions endpoint. Set contextWindow yourself — OpenClaw's custom-provider default is much smaller than 256k.

4. Reload and verify

openclaw gateway restart
openclaw models list

You should see camel-stream/deepseek-v4-flash with a 262k context window. If the gateway is already running as a daemon, restart it so it reloads the config.

openclaw dashboard

If OpenClaw cannot see the provider, confirm CAMEL_API_KEY is set in the same environment as the gateway and that the JSON5 file is valid.

What's next?