MiniMax M3.1 Flash Launches in Fireworks Serverless Preview
Thanks @FireworksAI_HQ for bringing M3.1 Flash to serverless on day 0! Looking sharp with the rebrand! 🎆
AI BriefingFireworks made M3.1 Flash available on serverless on the day its open weights were released. The preview will be open for two weeks, with its continued availability to be decided based on community demand. The quoted post gives benchmark scores of AutomationBench-AA 62.8, DeepSWE v1.1 73.7%, and BabyVision 91, with pricing of $0.15 per 1M input tokens / $0.60 per 1M output tokens / $0.015 per 1M cached tokens, half the price of M3. MiniMax reposted its thanks and recommended the model for multi-step agent workflows.
Source: MiniMax · x.com
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