MiniMax M1
MiniMax · released Jun 5, 2025 · MiniMaxAI/MiniMax-M1-40k
- Type
- Open weightsApache License 2.0
- Params
- 456B
- Context
- 1M
active per word not recorded by us · about 750K words of context
Our take
Written Sep 30, 2026MiniMax M1 is a downloadable text model built for long documents: it takes a large request in one go, and its licence allows commercial use, changes and redistribution. Its measured quality sits mid-field on the preference boards we hold, so treat it as a capacity and cost pick rather than a quality leader.
Reach for it when long documents would otherwise have to be split up first, and the bill matters more than peak quality — it is cheap to run through a host, and you can download it and run it yourself if you have hardware sized for it. Its licence allows commercial use, changes and redistribution (Apache License 2.0). Skip it if you need a model near the top of the preference boards, or if your work is text-only in a way that a smaller model already covers.
The case for it
- A request capacity that takes long documents without splitting them up first, though reliable recall across all of it is unverified in our data.
- The licence allows commercial use, changes and redistribution (Apache License 2.0), so building a product on it is permitted.
- Cheap to run through a host: the cheapest listed offer sits below the next host up on both input and output.
The case against it
- Mid-field on every preference board we hold — 117th of 168 on Arena Text (overall) as of 25 Sep 2026, and 118th of 168 on Arena Creative Writing as of 25 Sep 2026. These record which answers people preferred, not whether they were correct.
- 456.1 billion parameters in total with no active parameter count disclosed, so how much memory it needs in use is unverified in our data.
- Text in, text out: no image, audio or video input, so anything visual has to be described in words first.
How good is it?
EverydayGeneral questions and everyday reasoning
Arena Text (overall)117th of 168 · 1364
CodingWriting and fixing code on its own
Arena Coding117th of 168 · 1416
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing118th of 168 · 1319
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model6 scoresEvery figure we hold, from 6 boards, with who ran it and a link to the source — including the boards no rating above is built on.
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. 85.9 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 between 2 hours and 25 hours ago — each listing carries its own date.
- per 1M tokens
- $0.40 in / $2.20 out
- Context served
- 1M
- Throughput
- ~27 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.40 / $2.20checked 25 hours ago | 1M | not measured | Unknown | Unknown | Unknown |
| Novita AIbf16Direct and through OpenRouter | $0.55 / $2.20checked 2 hours ago | 1M40K max reply through OpenRouter | 14 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| MinimaxThrough OpenRouter | $0.40 / $2.20checked 2 hours ago | 1M40K max reply | 27 tok/s | No | Yesunknown period | Unknown |
OpenRouter
Novita AIAcross the 3 listings we hold: 2 say they do not train on prompts (1 of them only through OpenRouter), 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check (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 AIbf16Direct and through OpenRouter | ✓ | ✗ | ✗ |
| MinimaxThrough OpenRouter | ✗ | ✗ | ✗ |
Tool calling: 2 of 3 listings say yes, 1 says no. JSON output: 0 of 3 listings say yes, 3 say no. Strict schema: 0 of 3 listings say yes, 3 say no.
Models people weigh against MiniMax M1
When we formed this view
Recent changes
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.
- We do not hold the active parameter count for it, so how much of it runs on any one token is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings does not say whether it trains on prompts, and 1 answers only through OpenRouter, not for its own listing.
- We hold no cached-input rate for any of its listings.
- 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 allowsApache License 2.0, 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
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- MiniMaxAI/MiniMax-M1-40k
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- minimax-minimax-m1