Model directory
Choose a model for your next request.
Use the API id exactly as shown in the model field. Prices are USD per million tokens. Availability shows 10-minute checks over the last 24 hours.
Available models
-
AutoAvailable on Free
auto-freeOxRouterInput—Output—Cache—98.6% -
Auto CodingAvailable on Free
auto-free:codeOxRouterInput$0Output$0Cache$0100.0% -
GLM 5.3Available on Free
glm-5.3Z.AIInput—Output—Cache—83.3% -
GPT 6Available on Free
gpt-6OpenAIInput—Output—Cache—80.6%
- Successful checks
- Failed checks
- Mixed or incomplete
- No check
No models match these filters
Try another search or show all vendors.
Availability covers the last 24 hours, based on checks every 10 minutes. Each bar summarises about an hour: green means successful checks, red means failed checks, amber means mixed or incomplete checks, and pale means no check was recorded. Response time is the average of successful checks. Model access depends on your plan. Requests use POST /v1/chat/completions.