🚀 We’re launching MiniMax M3 from @MiniMax_AI on Novita AI as a Day-0 API launch partner.
The first open-weights model to combine:
• Frontier coding and agent capabilities
59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 74.2% MCP Atlas
• Up to 1M tokens of context
Enabled…
Excited to see Novita AI showing up as one of the most competitive providers for:
• DeepSeek-V4-Pro
• DeepSeek-V4-Flash
• Kimi-K2.6
Low cost, long context, production-ready inference ⚡
Thanks to @huggingface for making provider metrics more transparent across the…
Huge congrats to the @OpenRouter team on the $113M Series B 🎉
25T weekly tokens is a massive milestone — a clear signal that AI infra and agent workloads are entering true production scale.
Proud for Novita AI to be one of the leading providers powering the OpenRouter…
Qwen3.7-Max is now live on Novita AI！
Alibaba Cloud and Novita are teaming up to bring you the latest model built for the Agent Era.
Now go build something wild 🚀
Discuss this model
Add corrections, implementation notes, pricing changes, or usage caveats for other readers.