Chat Completions

Send tools and tool_choice in the OpenAI format. ZeroFA translates Claude and Gemini requests to their native formats and converts responses back to tool_calls. Streaming, non-streaming, and multi-turn tool results are supported.

{
  "model": "your-chat-model-id",
  "messages": [{"role": "user", "content": "What is the weather in Beijing?"}],
  "tools": [{
    "type": "function",
    "function": {
      "name": "get_weather",
      "description": "Get the current weather for a city",
      "parameters": {
        "type": "object",
        "properties": {"city": {"type": "string"}},
        "required": ["city"]
      }
    }
  }],
  "tool_choice": "auto"
}

When the model calls a tool, finish_reason is tool_calls and the call appears in message.tool_calls.

"message": {
  "role": "assistant",
  "content": "",
  "tool_calls": [{
    "id": "call_abc",
    "type": "function",
    "function": {
      "name": "get_weather",
      "arguments": "{\"city\":\"Beijing\"}"
    }
  }]
}

After executing the tool, send its result as a role: tool message with tool_call_id, together with the previous assistant tool_calls, so the model can continue.

messages[].content can be an array mixing text and image_url parts. Images can use data URLs or public URLs, and Claude and Gemini protocols are translated automatically.

{
  "model": "your-chat-model-id",
  "messages": [{
    "role": "user",
    "content": [
      {"type": "text", "text": "What is in this image?"},
      {"type": "image_url",
       "image_url": {"url": "data:image/png;base64,..."}}
    ]
  }]
}

Check the Vision capability badge on a model card to confirm image support.

With stream: true, the endpoint returns text/event-stream. Each chunk is a data: {...} line and the stream ends with data: [DONE].

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}

data: {"id":"chatcmpl-...","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

Every chat model works through this endpoint; change only model to switch. See the complete list and prices in the Model Catalog, or retrieve them with GET /v1/models.

See Errors and billing for complete details. Common errors include:

• 400 model_not_allowed — The model does not exist or the current plan cannot use it
• 402 insufficient_credits — The wallet balance is insufficient
• 429 rate_limited — An RPM or daily limit was exceeded, or upstream capacity is busy
• 503 upstream_unavailable — All upstream providers failed (uncommon)