Tool calling

Tool calling turns a model from a text generator into something that can act. You describe the tools available (name, purpose and parameter schema) and the model may respond with a request to call one, including arguments. Your application executes it and sends the result back as another message, and the model continues with that knowledge.

The model never runs anything itself. That boundary is the whole security story: you decide which tools exist, validate arguments before executing, and choose what to return.

curl https://api.webparam.com/v1/chat/completions \
  -H "Authorization: Bearer $WEBPARAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-coder",
    "messages": [{ "role": "user", "content": "What is the weather in Cape Town?" }],
    "tools": [{
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get current weather for a city",
        "parameters": {
          "type": "object",
          "properties": { "city": { "type": "string" } },
          "required": ["city"]
        }
      }
    }]
  }'

While the API is in build, you can explore the same models two ways: ask Echo how a request and response fit together, or browse the catalogue to compare pricing, context and capabilities.