One API key, hundreds of models — automatic failover and per-request price routing.
Conversational Chat
Multi-turn natural-language conversation with follow-up context.
Reasoning Mode
A deliberate "thinking" mode that works through multi-step problems before answering.
Multi-Model Switching
Core featurePick a different underlying model per task — fast, balanced or deep-reasoning.
Multilingual Support
Understands and replies in dozens of languages, including translation between them.
Long-Context Understanding
Handles very long documents and conversations without losing earlier context.
Text Generation
Drafts, rewrites and edits long-form and short-form copy.
Image Understanding
Reads photos, screenshots, diagrams and handwriting and answers questions about them.
Public API
OpenAI-compatibleA documented API for building the same capability into your own product.
Code Generation & Debugging
Writes, explains, reviews and fixes code across common languages.
Custom Assistants
Build and share a configured assistant with its own instructions and knowledge.
Task Automation
Schedules recurring jobs or runs multi-step tasks without supervision.
Third-Party Integrations
Connects to other SaaS products through apps, connectors or an integration platform.
Team Workspaces
Shared workspace with pooled seats, billing and admin management.
Shareable Links
Publish a conversation or output as a link others can open.
Export & Download
Export chats, documents or data out of the product in an open format.
Admin Controls & Roles
Central console for seats, roles, permissions and usage.
Data-Retention Controls
Configure how long conversation data is kept, or turn training off.
GDPR Compliance
Offers a data-processing agreement and EU data-protection commitments.
Encryption at Rest & in Transit
Traffic and stored data are encrypted with industry-standard ciphers.
Prices are set by the vendor and may change.
$0 /month
What's included
Per token usage
What's included
Small fee usage
What's included
Custom
What's included
OpenRouter is a routing layer in front of hundreds of AI models from dozens of providers. One API key and one OpenAI-compatible endpoint reach all of them — so switching model means changing a string, not rewriting an integration or signing another contract.
It handles the operational problems that come with using many providers: automatic failover when one is down, routing to the cheapest available host of a given model, unified billing, and one usage dashboard across everything.
Several models are available free, and there is no subscription — you pay only for tokens plus a small routing margin.
What the routing layer solves:
OpenRouter suits anyone building on more than one model.
If you are committed to a single provider long term, going direct avoids the routing margin.
More hosts per model, improving failover and price routing.
Use your own provider accounts while keeping routing and analytics.
Shared credits, member roles and team-level usage analytics.
More models made available at no cost for prototyping.
Join the users who trust OpenRouter for their daily tasks.