MiniMax released M3.1 Flash, nearly tripling inference speed and reducing usage costs by 70%
MiniMax M3.1 Flash: Redefining Agent Performance and Cost
AI BriefingMiniMax releases MiniMax M3.1 Flash. The anonymous model Space Bunny was an early version and had processed more than 200 trillion tokens.
Reported by 9 additional sources
- MiniMax releases M3.1 Flash, costing one-third as much as M3 and running about 3 times fasterX.PIN · 28 days ago
- MiniMax reveals that OpenRouter’s stealth model Space Bunny is actually M3.1 FlashMiniMax · 28 days ago
- MiniMax releases the M3.1 Flash reasoning model, reducing per-task costs to approximately $0.22The Decoder:AI News · 28 days ago
- MiniMax M3.1 Flash launches: inference speed nearly tripled, with usage costs reduced by 70%IT Home · Artificial Intelligence · 28 days ago
- MiniMax releases M3.1 Flash: a 428B MoE model with input priced at $0.15/1M tokensMarkTechPost · 28 days ago
- OpenCode reveals that Space Bunny is actually MiniMax M3.1 Flash, available for free for 3 daysopencode · 28 days ago
- OpenRouter reveals that the anonymous model Space Bunny is actually MiniMax M3.1 FlashOpenRouter · 28 days ago
- MiniMax releases M3.1 Flash: costs one-third as much as M3, runs 3 times faster, and will open its weights on October 23MiniMax · 28 days ago
- MiniMax releases M3.1 Flash: nearly 3× faster inference and 70% lower costsWeChat Official Account: MiniMax · 28 days ago
Source: MiniMax: Blog · minimax.io
Event follow-up3
View all event coverage- Unsloth releases quantized MiniMax-M3.1-Flash GGUF; the 2-bit version can run locally with 150GB of memoryUnsloth · 21 days ago
- MiniMax releases M3.1 Flash weights: 428B total parameters, 23B active per tokenMiniMax · 25 days ago
- MiniMax released M3.1 Flash, nearly tripling inference speed and reducing usage costs by 70%MiniMax:Blog · 28 days ago