Function calling (tools)

Describe the functions the model may call, and it decides on its own when a call is needed. The model does not run the function — it returns the function name and arguments, and your code performs the call. You send the result back into the conversation, and the model composes the final answer.

When the model decides to call a function, finish_reason is tool_calls and content is null. The arguments arrive in tool_calls[].function.arguments as a JSON string.

Function description

curl -X POST https://vibecode.bitrix24.com/v1/chat/completions \
  -H "X-Api-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bitrix/bitrixgpt-5.5",
    "messages": [
      {"role": "user", "content": "What is the weather in Berlin?"}
    ],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "Get the current weather in the specified city",
          "parameters": {
            "type": "object",
            "properties": {
              "city": {"type": "string", "description": "City name"}
            },
            "required": ["city"]
          }
        }
      }
    ],
    "tool_choice": "auto"
  }'

Response example

{
  "id": "chatcmpl-9aaee7576d8057ab",
  "object": "chat.completion",
  "model": "bitrix/bitrixgpt-5.5",
  "choices": [
    {
      "index": 0,
      "finish_reason": "tool_calls",
      "message": {
        "role": "assistant",
        "content": null,
        "tool_calls": [
          {
            "id": "chatcmpl-tool-a423212c4e614cab",
            "type": "function",
            "function": {
              "name": "get_weather",
              "arguments": "{\"city\": \"Berlin\"}"
            }
          }
        ]
      }
    }
  ],
  "usage": {"prompt_tokens": 275, "completion_tokens": 26, "total_tokens": 301}
}

Returning the result to the conversation

Run the function on your side and add a message to messages with the tool role and the same tool_call_id:

{
  "messages": [
    {"role": "user", "content": "What is the weather in Berlin?"},
    {"role": "assistant", "content": null, "reasoning_content": "The question is about the weather in a city — calling get_weather with city=Berlin.", "tool_calls": [{"id": "chatcmpl-tool-a423212c4e614cab", "type": "function", "function": {"name": "get_weather", "arguments": "{\"city\": \"Berlin\"}"}}]},
    {"role": "tool", "tool_call_id": "chatcmpl-tool-a423212c4e614cab", "content": "+5°C, cloudy"}
  ]
}

In its next response the model composes human-readable text based on the returned result.

A reasoning model reads the reasoning of every earlier assistant turn in such a conversation, so send it back in the reasoning_content field next to the tool_calls of the same message — otherwise the model loses the thread between calls. The acceptance rules for the field and its character limit — Create a chat completion.

Errors

The full list of common API errors — Errors.

Known specifics

Only type: "function" is supported. The endpoint has no built-in tools such as web search. A request with a different type value is rejected with 400 rather than silently executed without tools.

Names in the response are checked against your list. If the model invents a function name that is not in tools, that call is removed from the response. When all calls turn out to be invented, finish_reason switches to stop and a textual explanation arrives in content — the conversation does not loop on a nonexistent function.

Arguments arrive as a string. The arguments field is a JSON string, and you must parse it before use. The model can return syntactically valid JSON that does not match your parameter schema, so validate the values before the call.

See also

• Create a chat completion
• Guaranteed JSON response
• Web search
• List of models