MiniMax M3.1 Flash now available on AI Gateway for free
- Source
- vercel.com
- Author
- Zachary Chen
- Date
Context
Vercel's AI Gateway is offering MiniMax's M3.1 Flash free until Oct 22, but the free rate depends on which provider serves each request (vercel.com). AI Gateway is a single API in front of many model providers. Unless told otherwise, it picks the provider for each request based on recent uptime and latency (Vercel docs). The changelog says the free rate applies only when MiniMax itself serves the request, and tells developers to make sure of that by setting the provider order in the gateway's provider options. The pin does not end with the promotion: after the offer ends, pinned requests bill at MiniMax's standard rate.
The model is an model for coding and work, with a 1M-token . Vercel passes on MiniMax's claims that it improves on earlier MiniMax models at complex agentic tasks, coding and cybersecurity. On coding, MiniMax reports its best results on application development, particularly frontend interactions, targeted bug fixes and component tests. The changelog gives no benchmark figures for any of these claims.
- open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
- multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Checking sign-in…
Loading comments…