OpenRouter
One API for every major LLM — route to the cheapest or fastest provider automatically
OpenRouter is a unified LLM API that routes requests to the cheapest or fastest available provider for any given model. With a single API key you can access GPT-4o, Claude, Llama, Gemini, and hundreds of other models, with automatic fallback and cost optimisation.
The only API that lets you access every major LLM with a single key and automatically routes to the cheapest or fastest available provider.
- Single API for 200+ models across all major providers
- Automatic routing to cheapest or fastest provider
- Fallback and load balancing built in
- OpenAI-compatible API
- Free tier with rate-limited access to many models
- Adds a small latency overhead vs direct provider APIs
- Pricing is slightly above direct provider rates (routing fee)
- Less control over which specific provider handles your request
All Models
OpenRouter — Frequently Asked Questions
Community Reviews
All LLM Providers
Full comparison tableOpenRouter LLM pricing overview
OpenRouter is an inference API provider that hosts open-weight and third-party large language models. OpenRouter is a unified LLM API that routes requests to the cheapest or fastest available provider for any given model. With a single API key you can access GPT-4o, Claude, Llama, Gemini, and hundreds of other models, with automatic fallback and cost optimisation. Common use cases include Multi-model applications, Cost optimisation, Provider fallback, Prototyping. Headquartered in San Francisco, CA, founded 2023. All models are accessible via a REST API compatible with standard OpenAI-style request formats, enabling drop-in integration with most LLM frameworks and orchestration tools.
OpenRouter vs other LLM providers
OpenRouter competes with OpenAI, Anthropic, Google, Groq, Together AI, Mistral, Cohere, and other inference API providers across dimensions of price, throughput, latency, context window, and model intelligence. The only API that lets you access every major LLM with a single key and automatically routes to the cheapest or fastest available provider. Use the LLM provider comparison tool to see OpenRouter token pricing, latency, and throughput side-by-side with any other provider. The full LLM pricing table shows all providers ranked by input token cost, output token cost, and throughput in a single sortable view.
Why choose OpenRouter?
OpenRouter's key strengths are: Single API for 200+ models across all major providers; Automatic routing to cheapest or fastest provider; Fallback and load balancing built in. Limitations to consider: Adds a small latency overhead vs direct provider APIs; Pricing is slightly above direct provider rates (routing fee). For teams running high-volume inference workloads, prompt caching and batch API endpoints can reduce effective input token costs by 50–90% — check the context window cost guide for a full breakdown of caching economics.
Understanding OpenRouter token pricing
OpenRouter charges separately for input (prompt) and output (completion) tokens, priced per 1M tokens in USD. Output tokens are typically 3–5× more expensive than input tokens due to the compute cost of autoregressive generation. Prices shown are sourced from OpenRouter's public pricing page and updated daily. Need help estimating your spend? Read the LLM API cost calculator guide — it covers tokens, context windows, prompt caching, and batch discounts with worked examples for RAG, chat history, and document processing workloads.
OpenRouter context window and model capabilities
Context window size directly affects both capability and cost — every token in the context window is charged as an input token. For RAG and document processing workloads, longer context windows enable richer retrieval but increase per-call costs proportionally. Prompt caching — where supported — stores the KV state of repeated prefixes and charges 75–90% less for cache hits, making it the most impactful cost optimization for applications with consistent system prompts or retrieved documents. See the LLM context window cost guide for a full analysis of how context length affects your API bill.
Self-hosted vs managed inference: when OpenRouter makes sense
Managed inference APIs like OpenRouter eliminate infrastructure overhead — no GPU provisioning, driver management, or model serving stack to maintain. The trade-off is cost at scale: a single H100 at ~$2.50/hr can serve ~500K tokens/min of Llama 3.3 70B, which at OpenRouter API rates would cost significantly more per token. The break-even point depends on your request volume, latency requirements, and engineering capacity. For teams processing fewer than ~10M tokens/day, managed APIs are almost always cheaper when total cost of ownership is considered. Above that threshold, self-hosted inference on rented GPU compute typically wins on unit economics. Read the cheapest GPU cloud guide for a full break-even analysis. Historical OpenRouter token price data is available in the LLM price history charts.