OpenRouter Provider

Access 100+ models from multiple providers through OpenRouter's unified gateway using SimplerLLM.

Overview

OpenRouter acts as a unified gateway to access models from multiple providers (OpenAI, Anthropic, Google, Meta, and more) through a single API. SimplerLLM makes it easy to use any model available on OpenRouter.

What is OpenRouter?

OpenRouter provides access to 100+ models from different providers through a single API endpoint. You can switch between GPT-4, Claude, Llama, Gemini, and many others without changing your code - just change the model name.

Using OpenRouter Models

Model Examples

# OpenAI models through OpenRouter
model_name="openai/gpt-4o"

# Anthropic models through OpenRouter
model_name="anthropic/claude-3-5-sonnet"

# Google models through OpenRouter
model_name="google/gemini-pro"

# Meta models through OpenRouter
model_name="meta-llama/llama-3-70b"

# Any model from OpenRouter's catalog

Finding Available Models

Browse all 100+ available models at OpenRouter's model directory. New models are added regularly.

Setup and Authentication

Get Your API Key

1. Go to OpenRouter

2. Sign up or log in

3. Go to Keys section

4. Create a new API key

Configure Environment Variables

# .env file
OPENROUTER_API_KEY=your-openrouter-api-key-here

# Optional: Add your site info for better rankings
OPENROUTER_SITE_URL=https://your-site.com
OPENROUTER_SITE_NAME=Your App Name

Basic Usage

from SimplerLLM.language.llm import LLM, LLMProvider

# Create OpenRouter LLM instance
llm = LLM.create(
    provider=LLMProvider.OPENROUTER,
    model_name="openai/gpt-4o"  # Use any OpenRouter model
)

# Generate a response
response = llm.generate_response(
    prompt="Explain machine learning in simple terms"
)

print(response)

Switching Models

# Switch to Claude
llm = LLM.create(
    provider=LLMProvider.OPENROUTER,
    model_name="anthropic/claude-3-5-sonnet"
)

# Switch to Llama
llm = LLM.create(
    provider=LLMProvider.OPENROUTER,
    model_name="meta-llama/llama-3-70b"
)

# Switch to Gemini
llm = LLM.create(
    provider=LLMProvider.OPENROUTER,
    model_name="google/gemini-pro"
)

# All use the same SimplerLLM interface!

Advanced Features

Structured JSON Output

from pydantic import BaseModel, Field
from SimplerLLM.language.llm_addons import generate_pydantic_json_model

class Summary(BaseModel):
    title: str = Field(description="Title")
    points: list[str] = Field(description="Key points")

llm = LLM.create(
    provider=LLMProvider.OPENROUTER,
    model_name="openai/gpt-4o"  # Or any other model
)

result = generate_pydantic_json_model(
    llm_instance=llm,
    prompt="Summarize the benefits of cloud computing",
    model_class=Summary
)

print(f"Title: {result.title}")