OpenRouter Account Setup Guide
OpenRouter provides unified access to multiple AI models including Claude, GPT-4, Gemini, and more through a single API.
Getting Started
Step 2: Sign Up
Click "Sign In" in the top right corner. You can sign up using:
- Google account
- GitHub account
- Email address
Step 3: Add Credits
OpenRouter uses a pay-as-you-go model:
- Navigate to "Credits" in your dashboard
- Add funds (recommended: start with $5-$10)
- Accepted payment methods: Credit/Debit cards
Step 4: Generate API Key
Create your API key to use with Open WebUI:
- Go to https://openrouter.ai/keys
- Click "Create Key"
- Give it a name (e.g., "Open WebUI")
- Copy the generated key (starts with
sk-or-...)
⚠️ Important: Keep your API key secure! Don't share it publicly or commit it to version control.
Configuring Open WebUI
Step 5: Add OpenRouter to Open WebUI
Connect OpenRouter to your chat interface:
- Visit chat.thecapps.duckdns.org
- Click your profile icon → Settings
- Go to "Connections" → "OpenAI API"
- Set API Base URL:
https://openrouter.ai/api/v1
- Set API Key: Paste your OpenRouter key
- Click "Save" or "Verify Connection"
Step 6: Select Models
In Open WebUI, after connecting OpenRouter, you'll see available models automatically. The following premium models are recommended:
- Claude 3.7 Sonnet (Latest) - Best for reasoning, coding, and problem-solving
anthropic/claude-3.7-sonnet
- Claude 3.5 Sonnet - Stable version, excellent for general use
anthropic/claude-3.5-sonnet
- Gemini 2.0 Flash - Fast and cost-effective
google/gemini-2.0-flash-exp:free or google/gemini-2.0-flash-thinking-exp:free
- GPT-4o - General purpose excellence
openai/gpt-4o
- DeepSeek V3 - Great for technical tasks
deepseek/deepseek-chat
- Mistral Large - Multilingual support
mistralai/mistral-large
Note: Model IDs change as new versions are released. For the latest model IDs, visit https://openrouter.ai/models and copy the exact model ID from there.
Pricing Information
OpenRouter charges per token used:
- Claude 3.7 Sonnet: ~$3-15 per million tokens
- Claude 3.5 Sonnet: ~$3-15 per million tokens
- Gemini 2.0 Flash: Free tier available, then ~$0.15-0.60/M tokens
- GPT-4o: ~$2.50-10 per million tokens
- DeepSeek V3: ~$0.14-0.28 per million tokens (very affordable)
Important: Check current pricing at https://openrouter.ai/models as rates may change.
Usage Tips
- Monitor your usage in the OpenRouter dashboard
- Set up usage limits to avoid unexpected charges
- Use cheaper models for simple tasks, premium models for complex ones
- Enable caching in Open WebUI settings to reduce costs