OpenRouter Setup

Configure OpenRouter to access multiple AI models through a single API

OpenRouter provides a unified API to access models from multiple providers including OpenAI, Anthropic, Google, Meta, and more. It’s an excellent choice for flexibility and model variety.

Why Use OpenRouter?

• Multiple Models: Access GPT-4, Claude, Gemini, Llama, and dozens of other models
• Single API Key: One key for all models
• Cost Effective: Pay only for what you use
• No Subscriptions: No monthly fees required
• Model Routing: Automatically route to the best available model

Setup Steps

1. Get Your API Key

   1. Visit OpenRouter
   2. Sign up or log in to your account
   3. Navigate to the API Keys page
   4. Create a new API key
   5. Copy your API key (starts with sk-or-v1-...)
2. Configure Forge

   Run the interactive login command:

   forge provider login
   

   Select OpenRouter from the list and paste your API key when prompted.

3. Select a Model

   OpenRouter supports many models. Popular choices include:

   • anthropic/claude-sonnet-4-20250514 - Latest Claude Sonnet
   • openai/gpt-4o - GPT-4 Omni
   • google/gemini-2.5-pro - Gemini Pro
   • meta-llama/llama-3.3-70b-instruct - Llama 3.3

   Set your default model in forge.yaml:

   model: anthropic/claude-sonnet-4-20250514
   
4. Verify Connection

   Start Forge and test your setup:

   forge
   

   Try a simple prompt:

   > Hello! Can you confirm this is working?
   

Available Models

OpenRouter provides access to hundreds of models. To see all available models:

forge
# Then in the Forge session:
/model

Or visit the OpenRouter Models page.

Configuration

API Endpoint

• Chat Completions: https://openrouter.ai/api/v1/chat/completions
• Models List: https://openrouter.ai/api/v1/models

Authentication

OpenRouter uses API key authentication via the Authorization header.

Advanced Features

Model Selection

You can switch between models at any time using the /model command:

/model openai/gpt-4o

Cost Tracking

OpenRouter provides detailed usage and cost information in your dashboard. You can:

• Monitor spending in real-time
• Set spending limits
• View usage by model

Troubleshooting

Invalid API Key

If you see an authentication error:

1. Verify your API key is correct
2. Check that the key starts with sk-or-v1-
3. Ensure you’ve added credits to your OpenRouter account

Model Not Available

Some models require additional setup or credits:

1. Check the OpenRouter Models page
2. Ensure the model supports the features you need
3. Verify you have sufficient credits

Rate Limits

OpenRouter has rate limits that vary by model and plan:

• Check your current limits in the dashboard
• Consider upgrading your plan for higher limits
• Implement retry logic for production use

Deprecated: Environment Variable Setup

Using environment variables is deprecated. Please use forge provider login instead.

For backward compatibility, you can still use:

# .env
OPENROUTER_API_KEY=sk-or-v1-your-api-key

This will be automatically migrated to file-based storage on first run.

Next Steps

• Explore available models
• Learn about cost optimization
• Set up custom providers for additional flexibility