Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.tinfoil.sh/llms.txt

Use this file to discover all available pages before exploring further.

​
Function Calling

Function calling (also known as tool calling) lets AI models invoke external tools and APIs — fetching real-time data, performing calculations, or integrating with your existing systems.
Model Performance: Most chat models support function calling, but Kimi K2.6 and Kimi K2.5 offer exceptional tool calling capabilities. Kimi K2.6 is recommended for the strongest agentic workflows and complex tool calling scenarios. Note: GLM-5.1 does not currently support tool calling.

​
Basic Example

Here’s a simple example of how to implement function calling with a weather API: 
from tinfoil import TinfoilAI
import json

# Initialize client with Kimi K2.6 (recommended for tool calling)
client = TinfoilAI(
    api_key="<YOUR_API_KEY>"
)

# Define the tool/function
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather for a specific location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city and state, e.g. San Francisco, CA"
                    }
                },
                "required": ["location"]
            }
        }
    }
]

# Mock weather function (replace with real API call)
def get_weather(location):
    return f"The weather in {location} is sunny, 22°C"

# Make the initial request
response = client.chat.completions.create(
    model="<MODEL_NAME>",
    messages=[
        {"role": "user", "content": "What's the weather like in New York?"}
    ],
    tools=tools,
    tool_choice="auto"
)

# Check if the model wants to call a function
message = response.choices[0].message
if message.tool_calls:
    # Process each tool call
    for tool_call in message.tool_calls:
        if tool_call.function.name == "get_weather":
            # Parse function arguments
            args = json.loads(tool_call.function.arguments)
            location = args["location"]
            
            # Call the function
            weather_result = get_weather(location)
            
            # Send the function result back to the model
            messages = [
                {"role": "user", "content": "What's the weather like in New York?"},
                message,  # Assistant's message with tool call
                {
                    "role": "tool",
                    "content": weather_result,
                    "tool_call_id": tool_call.id
                }
            ]
            
            # Get the final response
            final_response = client.chat.completions.create(
                model="<MODEL_NAME>",
                messages=messages,
                tools=tools,
                tool_choice="auto"
            )
            
            print(final_response.choices[0].message.content)
else:
    print(message.content)

​
Multiple Tools Example

You can define multiple tools for more complex workflows: 
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string"}
                },
                "required": ["location"]
            }
        }
    },
    {
        "type": "function",
        "function": {
            "name": "calculate",
            "description": "Perform mathematical calculations",
            "parameters": {
                "type": "object",
                "properties": {
                    "expression": {
                        "type": "string",
                        "description": "Mathematical expression to evaluate"
                    }
                },
                "required": ["expression"]
            }
        }
    }
]

def calculate(expression):
    # Safe evaluation of mathematical expressions
    try:
        result = eval(expression)
        return str(result)
    except:
        return "Error: Invalid mathematical expression"

# The model can now choose between weather and calculation functions
response = client.chat.completions.create(
    model="<MODEL_NAME>",
    messages=[
        {"role": "user", "content": "What's 15 * 23 + 45?"}
    ],
    tools=tools,
    tool_choice="auto"
)

​
Best Practices

  1. Choose the Right Model: Among the models offered on Tinfoil API, Kimi K2.6 provides the strongest function calling and agentic workflow capabilities, while Kimi K2.5 remains an excellent option
  2. Clear Descriptions: Write detailed function descriptions to help the model understand when to use each tool
  3. Parameter Validation: Always validate function parameters before execution
  4. Error Handling: Implement proper error handling for function calls
  5. Security: Never execute untrusted code - validate all function arguments
  6. Testing: Test your functions independently before integrating with the AI model

Model catalog

View all available models and their capabilities.

Python SDK

Complete Python SDK documentation with more examples.