Fireworks AI has launched the MiniMax M3 model, offering it as the fastest endpoint for the MiniMax series. This new model boasts a 512K context window and supports native image and video input, along with significant speed improvements in prefill and decode through MSA sparse attention. The MiniMax M3 is priced comparably to its predecessor, the M2.7, and is recognized as a top open-weight model on the Artificial Analysis index. AI
IMPACT Enhances inference speed and multimodal capabilities for AI applications, potentially lowering costs for users.
RANK_REASON This is a product launch for an inference infrastructure provider, not a frontier model release from a core AI lab.
Read on X — Fireworks (inference infra) →
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
