Create an account to get started. You can set up an org for your team later.
Credits can be used with any model or provider.
Create an API key and start making requests. Fully OpenAI compatible.
Access all major models through a single, unified interface. OpenAI SDK works out of the box.
Reliable AI models via our distributed infrastructure. Fall back to other providers when one goes down.
Keep costs in check without sacrificing speed. OpenRouter runs at the edge, adding just ~25ms between your users and their inference.
Protect your organization with fine grained data policies. Ensure prompts only go to the models and providers you trust.
171.5B
Tokens/wk
2.4s
Latency
+8.82%
Weekly growth
171.5B
Tokens/wk
2.4s
Latency
+8.82%
Weekly growth
624.0B
Tokens/wk
1.8s
Latency
+4.04%
Weekly growth
SOTA image generation, character consistency, and multi-image outputs—now live with Gemini 2.5 Flash Image Preview.
After just one week on the platform, GPT-5 has taken the #1 spot for tool calling accuracy on OpenRouter. Here’s how the leaderboard looks and what this means for developers.
GPT-5 is here on OpenRouter — long-context, built for complex reasoning and code workflows.