​
Overview

OpenRouterLLMService provides access to OpenRouter’s language models through an OpenAI-compatible interface. It inherits from OpenAILLMService and supports streaming responses, function calling, and context management.

API Reference

Complete API documentation and method details

OpenRouter Docs

Official OpenRouter API documentation and features

Example Code

Working example with function calling

​
Installation

To use OpenRouterLLMService, install the required dependencies:

pip install "pipecat-ai[openrouter]"

You’ll also need to set up your OpenRouter API key as an environment variable: OPENROUTER_API_KEY.

Get your API key from OpenRouter. Free tier includes $1 of credits.

​
Frames

​
Input

  • OpenAILLMContextFrame - Conversation context and history
  • LLMMessagesFrame - Direct message list
  • VisionImageRawFrame - Images for vision processing (select models)
  • LLMUpdateSettingsFrame - Runtime parameter updates

​
Output

  • LLMFullResponseStartFrame / LLMFullResponseEndFrame - Response boundaries
  • LLMTextFrame - Streamed completion chunks
  • FunctionCallInProgressFrame / FunctionCallResultFrame - Function call lifecycle
  • ErrorFrame - API or processing errors

​
Function Calling

Function Calling Guide

Learn how to implement function calling with standardized schemas, register handlers, manage context properly, and control execution flow in your conversational AI applications.

​
Context Management

Context Management Guide

Learn how to manage conversation context, handle message history, and integrate context aggregators for consistent conversational experiences.

​
Usage Example

import os
from pipecat.services.openrouter.llm import OpenRouterLLMService
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.adapters.schemas.function_schema import FunctionSchema
from pipecat.adapters.schemas.tools_schema import ToolsSchema

# Configure OpenRouter service
llm = OpenRouterLLMService(
    api_key=os.getenv("OPENROUTER_API_KEY"),
    model="openai/gpt-4o-2024-11-20",  # Easy model switching
    params=OpenRouterLLMService.InputParams(
        temperature=0.7,
        max_tokens=1000
    )
)

# Define function for tool calling
weather_function = FunctionSchema(
    name="get_current_weather",
    description="Get current weather information",
    properties={
        "location": {
            "type": "string",
            "description": "City and state, e.g. San Francisco, CA"
        },
        "format": {
            "type": "string",
            "enum": ["celsius", "fahrenheit"],
            "description": "Temperature unit to use"
        }
    },
    required=["location", "format"]
)

tools = ToolsSchema(standard_tools=[weather_function])

# Create context
context = OpenAILLMContext(
    messages=[
        {
            "role": "system",
            "content": """You are a helpful assistant optimized for voice conversations.
            Keep responses concise and avoid special characters for better speech synthesis."""
        }
    ],
    tools=tools
)

# Create context aggregators
context_aggregator = llm.create_context_aggregator(context)

# Register function handler with feedback
async def fetch_weather(params):
    location = params.arguments["location"]
    await params.result_callback({"conditions": "sunny", "temperature": "75°F"})

llm.register_function("get_current_weather", fetch_weather)

# Optional: Add function call feedback
@llm.event_handler("on_function_calls_started")
async def on_function_calls_started(service, function_calls):
    await tts.queue_frame(TTSSpeakFrame("Let me check on that."))

# Use in pipeline
pipeline = Pipeline([
    transport.input(),
    stt,
    context_aggregator.user(),
    llm,
    tts,
    transport.output(),
    context_aggregator.assistant()
])

# Easy model switching for different use cases
# llm.set_model_name("anthropic/claude-3.5-sonnet")  # Switch to Claude
# llm.set_model_name("meta-llama/llama-3.1-70b-instruct")  # Switch to Llama

​
Metrics

Inherits all OpenAI metrics capabilities:

  • Time to First Byte (TTFB) - Response latency measurement
  • Processing Duration - Total request processing time
  • Token Usage - Prompt tokens, completion tokens, and totals

Enable with:

task = PipelineTask(
    pipeline,
    params=PipelineParams(
        enable_metrics=True,
        enable_usage_metrics=True
    )
)

​
Additional Notes

  • Model Variety: Access 70+ models from OpenAI, Anthropic, Meta, Google, and more
  • OpenAI Compatibility: Full compatibility with existing OpenAI code
  • Easy Switching: Change models with a single parameter update
  • Fallback Support: Built-in model fallbacks for high availability