MiniMax-M3.1-Flash
- In Input modalities: TextImageVideo Out Output modalities: Text
- Reasoning· low, medium, high, xhigh, max
- Tool use
- Open weights
Prices
2 offerings · prices as listedMiniMax-M3.1-Flash| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | $0.15 | $0.015 | $0.60 |
Prices from Pricing Overview - MiniMax API Docs (opens in a new tab) (checked Nov 1, 2026)
MiniMax-M3.1-Flash| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard | ¥1.00 | ¥0.10 | ¥4.00 |
Prices from MiniMax 按量计费价格 (opens in a new tab) (checked Nov 1, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Family
- minimax-m-flash
- Model ID
Not stated on MiniMax’s pages: max input, max thinking budget, structured output, built-in tools, knowledge cutoff, licence, aliases.
Run locally
Weights: MiniMaxAI/MiniMax-M3.1-Flash- Parameters 220.5B
- Active 23B · 128 experts, 4 per token
- Native precision BF16
- Layers 60
- KV cache per token 120 KB
- Config positions 1024K (config.json max_position_embeddings)
- API context 977K (maker’s API)
- Needs
- ≈ 115.5 GB (weights 109.1 + KV cache 0.9 + overhead 5.5)
- Usable
- 21.6 GB (90% of its memory)
- Try
- IQ2_XXS runs (needs system memory), but below 4 bits quality drops noticeably
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native)maker’s file | 232.9 GB | ≈ 245.5 | ✕Doesn’t fit | — |
| Q8_0 | 218.2 GB | ≈ 230.0 | ✕Doesn’t fit | — |
| FP8 | 205.3 GB | ≈ 216.6 | ✕Doesn’t fit | — |
| Q6_K | 168.6 GB | ≈ 178.0 | ✕Doesn’t fit | — |
| Q5_K_M | 146.1 GB | ≈ 154.3 | ✕Doesn’t fit | — |
| Q5_0 | 141.2 GB | ≈ 149.2 | ✕Doesn’t fit | — |
| Q4_K_M | 124.7 GB | ≈ 131.9 | ✕Doesn’t fit | — |
| Q4_0 | 115.5 GB | ≈ 122.2 | ✕Doesn’t fit | — |
| IQ4_XS | 109.1 GB | ≈ 115.5 | ✕Doesn’t fit | — |
| Q3_K_Mquality drops | 100.4 GB | ≈ 106.3 | ✕Doesn’t fit | — |
| IQ3_XXSquality drops | 78.5 GB | ≈ 83.4 | ✕Doesn’t fit | — |
| Q2_Kquality drops | 77.0 GB | ≈ 81.8 | ✕Doesn’t fit | — |
| IQ2_XXSquality drops | 52.9 GB | ≈ 56.5 | ○Needs system memory 22–33 tok/s | — |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): GPU NVIDIA B200 (HGX B200); unified memory Apple M5 Ultra (64-core GPU) · 256 GB.
Run commands
The maker publishes no files at this precision. Choose its native precision or one of its own builds, or quantise it yourself with llama.cpp.
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-06. How it’s estimated
Cited scores
From third-party leaderboards, not measured by us- LMArena WebDev 1,583
#33 of 94 listed models · CI 1,571–1,594 · 3,062 votes
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Oct 28, 2026
- changes we made
News
All news →- Oct 19, 2026Release MiniMax makes M3.1-Flash available MiniMax-M3.1-Flash is now available through the API. It supports a context window of up to 1,000,000 tokens and accepts text, image, and video inputs.
Changes
All changes →- Now priced on MiniMax API, China Input ¥1.00 · Output ¥4.00 · Cache read ¥0.10
- Now priced on MiniMax API Input $0.15 · Output $0.60 · Cache read $0.015
- New language model
Sources
- MiniMax text generation (opens in a new tab) platform.minimax.io · checked Nov 1, 2026
- MiniMax Anthropic-compatible API (opens in a new tab) platform.minimax.io · checked Nov 2, 2026
- MiniMax M3.1 Flash is Now Generally Available | MiniMax Agent Tools (opens in a new tab) agent.minimax.io · checked Nov 4, 2026
- Model Invocation (opens in a new tab) platform.minimax.io · checked Nov 2, 2026
- models.dev: minimax/MiniMax-M3.1-Flash (community data, MIT) (opens in a new tab) github.com · checked Oct 19, 2026
- 模型发布 - MiniMax 开放平台文档中心in Chinese (opens in a new tab) platform.minimaxi.com · checked Nov 2, 2026
- Pricing Overview - MiniMax API Docs (opens in a new tab) platform.minimax.io · checked Nov 1, 2026
- MiniMax 按量计费价格in Chinese (opens in a new tab) platform.minimaxi.com · checked Nov 1, 2026
- MiniMaxAI/MiniMax-M3.1-Flash config.json (opens in a new tab) huggingface.co · checked Nov 2, 2026
- MiniMaxAI/MiniMax-M3.1-Flash model card (opens in a new tab) huggingface.co · checked Nov 2, 2026
- MiniMaxAI/MiniMax-M3.1-Flash files (opens in a new tab) huggingface.co · checked Nov 5, 2026
- MiniMaxAI/MiniMax-M3.1-Flash README.md (opens in a new tab) huggingface.co · checked Nov 5, 2026
MiniMax’s official policies: data use, privacy, terms →
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
MiniMax · China · minimax.io
Related models
Snapshots, the same family and other models from this provider