MiniMax names Inferact an API launch partner for M3.1 Flash
MiniMax said on X that Inferact is an API launch partner for its M3.1 Flash model, crediting the partner's vLLM expertise for the serving collaboration and saying the two will keep building serving infrastructure for complex agent workloads. Inferact said it is working with MiniMax on production inference for the model, which it describes as built for multi-step automation, real-codebase engineering and visual reasoning. The partner-stated text also cites a score of 29.6 on Agents' Last Exam (ALE); no independent measurement was provided.
The post adds a production-inference and vLLM serving partner for M3.1 Flash, but its capability claims and the ALE score come from MiniMax's partner rather than independent testing.
Great to have Inferact as an API launch partner for M3.1 Flash! Thanks for bringing your vLLM expertise to the collaboration. Excited to keep building the serving infrastructure for complex agent workloads together.
Inferact: Inferact is an API launch partner for MiniMax M3.1 Flash! 🎉 We're working with @MiniMax_AI on production inference for its latest model, built for multi-step automation, real-codebase engineering and visual reasoning. M3.1 Flash scored 29.6 on Agents’ Last Exam (ALE),