Skip to main content

Tool Calling

Tool calling is a mechanism that allows large models to interact with external systems, enabling models to call external tools to extend their capabilities beyond pure text generation.

1. Supported Models​

GLM

  • GLM-5.1
  • GLM-5
  • GLM-4.7

Minimax

  • MiniMax-M2.5
  • MiniMax-M2.1

2. Usage​

2.1 Request via OpenAI Library​

from openai import OpenAI
import json

client = OpenAI(
    base_url="https://api.jalapeno-cloud.ai/v1/chat/completions", 
    api_key="${API_KEY}"
)

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "parameters": {"type": "object", "properties": {"city": {"type": "string"}}}
    }
}]

2.2 Add tools parameter via REST API​

{
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "get_weather",
                "parameters": {"type": "object", "properties": {"city": {"type": "string"}}}
            }
        }
    ]
}

3. Tool Calling Example​

from openai import OpenAI
import json

client = OpenAI(
    base_url="https://api.jalapeno-cloud.ai/v1/chat/completions", 
    api_key="${API_KEY}"
)

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "parameters": {"type": "object", "properties": {"city": {"type": "string"}}}
    }
}]

messages = [{"role": "user", "content": "What's the weather like in Beijing?"}]

# First call, model returns tool call request
resp = client.chat.completions.create(
    model="${MODEL_NAME}",
    messages=messages,
    tools=tools,
    tool_choice="auto"
)

# Get tool call
tool_call = resp.choices[0].message.tool_calls[0]
args = json.loads(tool_call.function.arguments)

# Simulate tool execution
weather_result = f"{args['city']} sunny 25°C"

# Second call, send result back to model
messages.append(resp.choices[0].message)
messages.append({"role": "tool", "tool_call_id": tool_call.id, "content": weather_result})

final = client.chat.completions.create(
    model="${MODEL_NAME}",
    messages=messages
)

print(final.choices[0].message.content)

Response​

<think>Okay, I've got the weather information for Beijing. Now I need to respond to the user in a friendly way.
</think>
Today's weather in Beijing is **sunny** with a temperature of **25°C**. The weather is nice, perfect for outdoor activities! Remember to protect yourself from the sun and stay hydrated.