OpenRouter
A unified interface for LLMs
OpenRouter provides a unified API for accessing hundreds of AI models from multiple providers. It aggregates models from OpenAI, Anthropic, Google, Meta, Mistral, and many others, offering a single endpoint with automatic fallback routing and provider optimization.
LLM API Pricing
Pay-per-token pricing. Prices shown per 1M tokens.
Prices last updated: April 18, 2026
| Model | Creator | Context | Input/1M | Output/1M | Updated |
|---|---|---|---|---|---|
| IBM | 131K | $0.017 | $0.110 | 4/18/2026 | |
| Mistral | 131K | $0.020 | $0.040 | 4/18/2026 | |
| Meta | 128K | $0.020 | $0.050 | 4/18/2026 | |
| Meta | 128K | $0.027 | $0.200 | 4/18/2026 | |
| 8K | $0.030 | $0.090 | 4/14/2026 | ||
| Meta | 8K | $0.030 | $0.040 | 4/18/2026 | |
| OpenAI | 128K | $0.030 | $0.140 | 4/18/2026 | |
| Alibaba | 33K | $0.030 | $0.090 | 4/14/2026 | |
| Alibaba | 128K | $0.033 | $0.130 | 4/18/2026 | |
| Amazon | 128K | $0.035 | $0.140 | 4/18/2026 | |
Pros & Cons
Advantages
- Largest selection of models through a single API
- Transparent per-token pricing with no markup on many models
- Automatic failover across multiple providers
- No vendor lock-in — switch models with a single parameter change
- Supports prompt caching for cost savings
- Free tier available for select models
Limitations
- Aggregator pricing may include a small margin on some models
- Latency may be slightly higher due to routing layer
- No fine-tuning or custom model training
Key Features
Unified Model Access
Single API endpoint for 300+ models from dozens of providers
Automatic Fallback Routing
Requests automatically route to the best available provider for each model
OpenAI-Compatible API
Drop-in replacement using the OpenAI SDK format
Provider Optimization
Routes to the fastest or cheapest provider based on your preference
Usage-Based Pricing
Pay per token with no minimum commitments or subscriptions
Prompt Caching
Reduced pricing for cached input tokens on supported models
Pricing Options
| Option | Details |
|---|---|
| Pay-per-token | Usage-based pricing per input and output token, varying by model |
| Prompt caching | Discounted rates for cached input tokens on supported models |
| Free models | Select open-source models available at no cost |
Availability & Support
Regions
Global — routes to providers across multiple regions for optimal latency
Support
Documentation, Discord community, and email support
Getting Started
- 1
Create an account
Sign up at openrouter.ai
- 2
Get API key
Generate an API key from your dashboard
- 3
Choose a model
Browse 300+ models across text, image, audio, and video
- 4
Make API calls
Use OpenAI-compatible endpoints with your OpenRouter key