MiniMax M2.1
MiniMax · released Dec 20, 2025 · MiniMaxAI/MiniMax-M2.1
- Type
- Open weightsCustom licence
- Params
- 229B
- Context
- 205K
10B active per word · about 154K words of context · download allowed, licence restricts use
Our take
Written Sep 2, 2026MiniMax M2.1 is a 229-billion-parameter text-only model with a 204,800-token request limit and a custom restricted licence. It offers multiple hosted providers at the same base rate, though no benchmark scores are available to verify its quality.
Pick this for long-document text work that needs more than the common 128-thousand-token limit, or when you want provider choice at a single predictable rate. Use the standard tier for speed; it is four times faster than the premium tier at half the output cost. Skip it if you need measured quality data, a permissive open-source licence, or any image, audio or video input.
The case for it
- 204,800-token request limit — well above the common 128-thousand baseline for long-document work.
- Three independent hosts at the same base rate, giving real provider choice.
- Standard tier reaches 80 tokens per second, the fastest measured option.
The case against it
- Premium tier is four times slower at twice the output cost — a poor speed-for-price trade.
- No benchmark scores recorded; quality is entirely unverified in our data.
- Custom licence may limit commercial use, redistribution or modification versus standard open-source terms.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M3 Ultra (80-core GPU) · 512 GB
Room to spare. 233.8 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.30 in / $1.20 out
- Context served
- 205K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.30 / $1.20checked 4 hours ago | 205K | not measured | Unknown | Unknown | Unknown |
| Novita AIfp8Direct and through OpenRouter | $0.30 / $1.20checked 4 hours ago | 205K131K max reply through OpenRouter | 40 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Minimaxfp8Through OpenRouter | $0.30 / $1.20checked 4 hours ago | 205K131K max reply | 66 tok/s | No | Yesunknown period | Confirmed |
| Minimaxhighspeed tierfp8Through OpenRouter | $0.30 / $2.40checked 4 hours ago | 205K131K max reply | 19 tok/s | No | Yesunknown period | Unknown |
Novita AIAcross the 4 listings we hold: 3 say they do not train on prompts (1 of them only through OpenRouter), 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check (1 of them only through OpenRouter); the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✗ |
| Novita AIfp8Direct and through OpenRouter | ✓ | ✓ | ✗ |
| Minimaxfp8Through OpenRouter | ✓ | ✓ | ✗ |
| Minimaxhighspeed · fp8Through OpenRouter | ✓ | ✓ | ✗ |
Tool calling: 4 of 4 listings say yes. JSON output: 4 of 4 listings say yes. Strict schema: 0 of 4 listings say yes, 4 say no.
Models people weigh against MiniMax M2.1
When we formed this view
Recent changes
What moved
output −50% ($2.40 → $1.20 per 1M tokens)What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 4 listings does not say whether it trains on prompts, and 1 answers only through OpenRouter, not for its own listing.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsCustom licence, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Custom licence
This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.
Identifiers
- Hugging Face
- MiniMaxAI/MiniMax-M2.1
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- minimax-minimax-m2-1