Imported from jeremylongshore/tons-of-skills-marketplace (skills/.curated/openrouter-function-calling/SKILL.md). Install upstream with npx skills add jeremylongshore/tons-of-skills-marketplace --skill openrouter-function-calling. Copyright stays with the author (MIT).

OpenRouter Function Calling

Overview

OpenRouter supports OpenAI-compatible tool/function calling across multiple providers. Define tools as JSON Schema, send them with your request, and the model returns structured tool_calls instead of free text. This works with GPT-4o, Claude 3.5, Gemini, and other tool-capable models via the same API. The key difference from direct provider APIs: OpenRouter normalizes the tool calling interface, so the same code works across providers.

Prerequisites

• An OpenRouter API key (sk-or-v1-...) exported as OPENROUTER_API_KEY — see the openrouter-install-auth skill for setup
• Python 3.8+ or Node.js 18+ with the OpenAI SDK (pip install openai / npm install openai)
• A tool-capable model — check the Model Compatibility table below or query /api/v1/models (e.g., openai/gpt-4o, anthropic/claude-3.5-sonnet)
• Real function implementations to dispatch tool calls to (the execute_tool() dispatcher below stubs get_weather and search_database)

Instructions

1. Pick a model from the Model Compatibility table that supports the features you need (tool calling, JSON mode, parallel tools).
2. Define your tools as JSON Schema per Basic Tool Calling and send them with tool_choice="auto" (or "required" to force a call, or a specific function name).
3. Read response.choices[0].message.tool_calls — each entry carries function.name and JSON-encoded function.arguments to parse with json.loads().
4. For agents, wire the Multi-Turn Tool Loop: append the assistant message, execute each tool via execute_tool(), append role: "tool" results keyed by tool_call_id, and loop until the model returns plain text (bounded by max_rounds).
5. Use the TypeScript Tool Calling section for the identical flow in Node — same schema, same tool_calls shape.
6. When you only need structured data (no function execution), skip tools and use Structured Output (JSON Mode) with response_format={"type": "json_object"}.
7. Handle failures per the Error Handling table: force tool_choice: "required" for extraction pipelines and validate arguments server-side before executing.

Basic Tool Calling

import os, json
from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key=os.environ["OPENROUTER_API_KEY"],
    default_headers={"HTTP-Referer": "https://my-app.com", "X-Title": "my-app"},
)

# Define tools with JSON Schema
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string", "description": "City name"},
                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
                },
                "required": ["location"],
            },
        },
    },
    {
        "type": "function",
        "function": {
            "name": "search_database",
            "description": "Search the product database",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {"type": "string"},
                    "limit": {"type": "integer", "default": 10},
                },
                "required": ["query"],
            },
        },
    },
]

response = client.chat.completions.create(
    model="anthropic/claude-3.5-sonnet",  # Also works with openai/gpt-4o, etc.
    messages=[{"role": "user", "content": "What's the weather in Tokyo?"}],
    tools=tools,
    tool_choice="auto",  # "auto" | "required" | "none" | {"type":"function","function":{"name":"..."}}
    max_tokens=1024,
)

message = response.choices[0].message
if message.tool_calls:
    for tc in message.tool_calls:
        print(f"Function: {tc.function.name}")
        print(f"Args: {json.loads(tc.function.arguments)}")
        # → Function: get_weather
        # → Args: {"location": "Tokyo", "unit": "celsius"}

Multi-Turn Tool Loop

def tool_loop(user_prompt: str, tools: list, model: str = "openai/gpt-4o", max_rounds: int = 5):
    """Execute tool calls in a loop until the model returns a text response."""
    messages = [{"role": "user", "content": user_prompt}]

    for _ in range(max_rounds):
        response = client.chat.completions.create(
            model=model, messages=messages, tools=tools, max_tokens=1024,
        )
        msg = response.choices[0].message
        messages.append(msg)  # Add assistant message (with tool_calls)

        if not msg.tool_calls:
            return msg.content  # Final text response

        # Execute each tool call and feed results back
        for tc in msg.tool_calls:
            result = execute_tool(tc.function.name, json.loads(tc.function.arguments))
            messages.append({
                "role": "tool",
                "tool_call_id": tc.id,
                "content": json.dumps(result),
            })

    return "Max tool rounds exceeded"

def execute_tool(name: str, args: dict) -> dict:
    """Dispatch to actual function implementations."""
    TOOLS = {
        "get_weather": lambda **kw: {"temp": 22, "condition": "sunny", "location": kw["location"]},
        "search_database": lambda **kw: {"results": [f"Product matching '{kw['query']}'"], "count": 1},
    }
    fn = TOOLS.get(name)
    if not fn:
        return {"error": f"Unknown tool: {name}"}
    try:
        return fn(**args)
    except Exception as e:
        return {"error": str(e)}

# Usage
result = tool_loop("What's the weather in Tokyo and find me umbrella products?", tools)
print(result)

TypeScript Tool Calling

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://openrouter.ai/api/v1",
  apiKey: process.env.OPENROUTER_API_KEY,
  defaultHeaders: { "HTTP-Referer": "https://my-app.com", "X-Title": "my-app" },
});

const tools: OpenAI.ChatCompletionTool[] = [
  {
    type: "function",
    function: {
      name: "calculate",
      description: "Evaluate a math expression",
      parameters: {
        type: "object",
        properties: { expression: { type: "string" } },
        required: ["expression"],
      },
    },
  },
];

const response = await client.chat.completions.create({
  model: "openai/gpt-4o",
  messages: [{ role: "user", content: "What is 42 * 17 + 3?" }],
  tools,
  tool_choice: "auto",
  max_tokens: 512,
});

const toolCalls = response.choices[0].message.tool_calls;
if (toolCalls) {
  for (const tc of toolCalls) {
    const args = JSON.parse(tc.function.arguments);
    console.log(`${tc.function.name}(${JSON.stringify(args)})`);
  }
}

Structured Output (JSON Mode)

# Force JSON output without tool calling (simpler for extraction tasks)
response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[
        {"role": "system", "content": "Extract data as JSON with fields: name, email, company"},
        {"role": "user", "content": "Contact Jane Smith at jane@acme.co, she works at Acme Corp"},
    ],
    response_format={"type": "json_object"},
    max_tokens=200,
)
data = json.loads(response.choices[0].message.content)
# → {"name": "Jane Smith", "email": "jane@acme.co", "company": "Acme Corp"}

Model Compatibility

Output

The tool-calling flows produce:

• message.tool_calls entries — each with a function.name and JSON-encoded function.arguments (e.g., get_weather with {"location": "Tokyo", "unit": "celsius"}) plus a tool_call_id for pairing results
• The final assistant text once the Multi-Turn Tool Loop resolves — or the "Max tool rounds exceeded" sentinel if it hits max_rounds
• From JSON Mode: a parseable JSON object matching your system-prompt schema (e.g., {"name": "Jane Smith", "email": "jane@acme.co", "company": "Acme Corp"})

Examples

Asking a weather question with the get_weather tool registered:

message = response.choices[0].message
for tc in message.tool_calls:
    print(tc.function.name, json.loads(tc.function.arguments))
# get_weather {'location': 'Tokyo', 'unit': 'celsius'}

Feed that result back as a role: "tool" message and the next completion returns prose ("It's currently 22°C and sunny in Tokyo..."). More worked examples: references/examples.md.

Error Handling

Enterprise Considerations

• Not all models support tool calling -- check model capabilities via /api/v1/models before sending tools
• Use tool_choice: "required" when you must get a tool call (e.g., extraction pipelines)
• Validate tool arguments server-side before executing -- models can hallucinate argument values
• Set max_tokens to prevent expensive completion when model decides not to use tools
• Use fallback chain with tool-capable models only (see openrouter-fallback-config)
• Log tool call names and arguments for audit trails (redact sensitive args)

References

• Examples | Errors
• Tool/Function Calling | API Reference