Use Pi

Pi can add custom providers in ~/.pi/agent/models.json. Camel Stream exposes /v1/responses.

1. Install Pi

npm install -g --ignore-scripts @earendil-works/pi-coding-agent

See the Pi quickstart for other install options.

2. Create a Stream key

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

export CAMEL_API_KEY="qaml_live_..."

3. Register Camel Stream

Merge this into ~/.pi/agent/models.json. Keep any providers you already have. The file reloads when you open /model.

{
  "providers": {
    "camel-stream": {
      "baseUrl": "https://stream.camelai.com/v1",
      "api": "openai-responses",
      "apiKey": "$CAMEL_API_KEY",
      "authHeader": true,
      "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 }
        }
      ]
    }
  }
}

$CAMEL_API_KEY is read from the environment. You can also run /login inside Pi and paste the key for the camel-stream provider. See Pi custom models and Pi providers.

4. Select the model

cd /path/to/your/project
pi

Then run /model and choose camel-stream/deepseek-v4-flash. If the model is listed but unavailable, the key is missing from the environment.

What's next?