MiniMax M3.1 Flash: Benchmarks, Pricing & Context Window
MiniMax M3.1 Flash is a language model from MiniMax, released in October 2026, with multimodal input, a 1M-token context window, and pricing from $0.150/M input, $0.015/M cached input, $0.600/M output.
MiniMax M3.1 Flash is the flash successor in the MiniMax M3 family, released 2026-10-19. It is a multimodal reasoning model with a 1M-token context window, native image and video input, and text output. Thinking is always on (cannot be
MiniMax M3.1 Flash benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for MiniMax M3.1 Flash across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How MiniMax M3.1 Flash holds up as conversations get longer.
Quality Tracker
MiniMax M3.1 Flash Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Mon Oct 19 2026MiniMax M3.1 Flash pricing
Providers
MiniMax M3.1 Flash starts at $0.150 per million input tokens and $0.600 per million output tokens via MiniMax. Reused prompt prefixes cost $0.0150 per million cached input tokens.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 MiniMax | $0.150 | $0.0150 | $0.600 | 1.0M/524.3K | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
MiniMax M3.1 Flash context window
Input and output token limits for MiniMax M3.1 Flash, plus how it ranks on long-context understanding.
Try now
huggleMake it with
MiniMax M3.1 Flash.
MiniMax M3.1 Flash latency
MiniMax M3.1 Flash time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
MiniMax M3.1 Flash examples
Recent arena outputs from MiniMax M3.1 Flash, picked from the highest-ranked matchups.
MiniMax M3.1 Flash license
MiniMax M3.1 Flash is a proprietary model available under its provider's product and API terms.
- License
- Proprietary
- Hosted access
Proprietary license - usage restrictions apply
MiniMax M3.1 Flash resources
Official sources for MiniMax M3.1 Flash: provider documentation, official playground, official launch post.
MiniMax M3.1 Flash vs other models
The most-compared alternatives to MiniMax M3.1 Flash are GPT-5.2, GPT-6 Astra, GPT-5.5 Instant. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like MiniMax M3.1 Flash
Models ranked just above and below MiniMax M3.1 Flash by LLM Stats score.
FAQ
Common questions about MiniMax M3.1 Flash.