MiniMax releases M3.1 Flash, claiming nearly 3x faster inference and 70% lower agent-task cost
What happened
On October 19, 2026, MiniMax released M3.1 Flash and published its performance and pricing details. MiniMax says online inference is nearly three times faster and that the overall usage cost for agent tasks is 70% lower than the previous generation. On DeepSWE v1.1 the model scores 73.7%, and everyday output reaches 200+ TPS. Pricing per million tokens is $0.15 for input, $0.60 for output and $0.015 for cached input. The report covers only the release and these performance, cost and price figures.
Written by AI from the coverage · updated 1 hour ago
Coverage
Follow the reports to see the story from different sides.
- AI HOT · ModelsPickMiniMax releases M3.1 Flash with nearly 3x faster inference and 70% lower usage cost
MiniMax released M3.1 Flash, which it says runs online inference nearly three times faster and cuts overall usage cost on agent tasks by 70% versus the previous generation. The model scores 73.7% on DeepSWE v1.1 and reaches 200+ TPS in everyday output. Pricing is $0.15 per 1M input tokens, $0.60 per 1M output tokens and $0.015 per 1M cached input tokens.
Heat over time
Not enough continuous observations to draw a trend yet.