← Models
Compare
Compare pricing, specifications, performance, and benchmarks for up to four models.
+ Add model · 0/4
Select at least two models, or choose a popular comparison below.
What a comparison shows
Every comparison puts 2 to 4 models side by side on the same objective metrics.
- Pricing per million input and output tokens, with any active discount applied.
- Context length and maximum output length.
- Time to First Token and throughput, as rolling averages measured on AIHubMix.
- LMArena benchmarks, where the model has been rated.
- Real usage on AIHubMix: weekly requests and token trends.
- A monthly cost estimate for your own request volume.
How it works
- Add models with the picker above. The URL holds your selection, so a comparison can be shared or bookmarked.
- Figures are a cached snapshot; the page states when it was taken and refreshes on demand.
- Every model on AIHubMix is callable through one API key and one base URL, so the prices below are what you would actually pay.
Popular comparisons
Related model match-ups readers also look at.
AIHubMix