VercelVercel
Menu

Tool Calls

Last updated January 15, 2026

The AI Gateway supports OpenAI-compatible function calling, allowing models to call tools and functions. This follows the same specification as the OpenAI Function Calling API.

Basic tool calls

tool-calls.ts
import OpenAI from 'openai';
 
const apiKey = process.env.AI_GATEWAY_API_KEY || process.env.VERCEL_OIDC_TOKEN;
 
const openai = new OpenAI({
  apiKey,
  baseURL: 'https://ai-gateway.vercel.sh/v1',
});
 
const tools: OpenAI.Chat.Completions.ChatCompletionTool[] = [
  {
    type: 'function',
    function: {
      name: 'get_weather',
      description: 'Get the current weather in a given location',
      parameters: {
        type: 'object',
        properties: {
          location: {
            type: 'string',
            description: 'The city and state, e.g. San Francisco, CA',
          },
          unit: {
            type: 'string',
            enum: ['celsius', 'fahrenheit'],
            description: 'The unit for temperature',
          },
        },
        required: ['location'],
      },
    },
  },
];
 
const completion = await openai.chat.completions.create({
  model: 'anthropic/claude-sonnet-4.5',
  messages: [
    {
      role: 'user',
      content: 'What is the weather like in San Francisco?',
    },
  ],
  tools: tools,
  tool_choice: 'auto',
  stream: false,
});
 
console.log('Assistant:', completion.choices[0].message.content);
console.log('Tool calls:', completion.choices[0].message.tool_calls);
tool-calls.py
import os
from openai import OpenAI
 
api_key = os.getenv('AI_GATEWAY_API_KEY') or os.getenv('VERCEL_OIDC_TOKEN')
 
client = OpenAI(
    api_key=api_key,
    base_url='https://ai-gateway.vercel.sh/v1'
)
 
tools = [
    {
        'type': 'function',
        'function': {
            'name': 'get_weather',
            'description': 'Get the current weather in a given location',
            'parameters': {
                'type': 'object',
                'properties': {
                    'location': {
                        'type': 'string',
                        'description': 'The city and state, e.g. San Francisco, CA'
                    },
                    'unit': {
                        'type': 'string',
                        'enum': ['celsius', 'fahrenheit'],
                        'description': 'The unit for temperature'
                    }
                },
                'required': ['location']
            }
        }
    }
]
 
completion = client.chat.completions.create(
    model='anthropic/claude-sonnet-4.5',
    messages=[
        {
            'role': 'user',
            'content': 'What is the weather like in San Francisco?'
        }
    ],
    tools=tools,
    tool_choice='auto',
    stream=False,
)
 
print('Assistant:', completion.choices[0].message.content)
print('Tool calls:', completion.choices[0].message.tool_calls)

Controlling tool selection: By default, tool_choice is set to 'auto', allowing the model to decide when to use tools. You can also:

  • Set to 'none' to disable tool calls
  • Force a specific tool with: tool_choice: { type: 'function', function: { name: 'your_function_name' } }

Tool call response format

When the model makes tool calls, the response includes tool call information:

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "anthropic/claude-sonnet-4.5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": null,
        "tool_calls": [
          {
            "id": "call_123",
            "type": "function",
            "function": {
              "name": "get_weather",
              "arguments": "{\"location\": \"San Francisco, CA\", \"unit\": \"celsius\"}"
            }
          }
        ]
      },
      "finish_reason": "tool_calls"
    }
  ],
  "usage": {
    "prompt_tokens": 82,
    "completion_tokens": 18,
    "total_tokens": 100
  }
}

Was this helpful?

supported.