How do I test tool calling with cURL?

Step 1: send the tools. The reply has finish_reason: "tool_calls" and a tool_calls array.

curl https://api.gateway.clatterlabs.xyz/v1/chat/completions \
  -H "Authorization: Bearer $CLATTER_API_KEY" \
  -H "X-Clatter-Account: $CLATTER_ACCOUNT_ID" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "supercosmos-max",
    "messages": [{"role": "user", "content": "What is the weather in Paris?"}],
    "tools": [{"type": "function", "function": {
      "name": "get_weather",
      "description": "Get the current weather for a city.",
      "parameters": {"type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"]}
    }}]
  }'

Step 2: send the conversation again with the assistant message (including its tool_calls) and a {"role": "tool", "tool_call_id": "<id>", "content": "..."} message, and the model writes its final answer.

Set CLATTER_API_KEY (a clsk_ key with models:invoke) and CLATTER_ACCOUNT_ID (your CL- Account ID from Console › Settings) first. Reference: Model API reference.

Good to know#

• Every response has an X-Request-Id; log it so a request can be found later. Why log it
• If calls fail unexpectedly, check status.clatterlabs.com before debugging further.
• Your key's account is responsible for your end users' text under the Abuse policy. What it means for apps

Still need help?#

• General support: support@clatterlabs.com or team@clatterlabs.xyz
• Infrastructure questions, or permanent deletion of your data (your whole account or one service): infrastructure@clatterlabs.xyz

We usually reply within the first hour, and always within 24 hours. A full support team is with you.