MiniMax M1
MiniMax · released Jun 17, 2025 · MiniMaxAI/MiniMax-M1-40k
- Type
- Open weightsApache License 2.0
- Params
- Not published
- Context
- 1M
about 750K words of context
Our take
Written Aug 3, 2026MiniMax M1 is a downloadable text model with a one-million-token request limit and a permissive Apache licence. Its measured coding score is the strongest of its six tracked skills, while its creative-writing score lags almost a hundred points behind.
Choose this for long-document processing at one million tokens, rare among downloadable models. Use it for coding tasks, where it scores highest among its own measured dimensions. Pick direct MiniMax access for the lowest input rate without third-party markup. Skip it if you need strong creative writing, consistent speed across providers, or any basis to judge hardware requirements.
The case for it
- One-million-token request limit, extremely long among downloadable models.
- Coding performance leads its own skill profile: a 98.6-point gap above its creative-writing score on the same evaluation framework.
- Direct access avoids the premium charged by third-party routers.
The case against it
- Creative writing is the weakest of its six measured skills, almost a hundred points below its coding score.
- Throughput more than doubles between providers, so speed depends heavily on where you run it.
- Parameter count is undisclosed, leaving no basis to judge efficiency or hardware needs.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)95th of 143 · 1363.8
CodingWriting and fixing code on its own
Arena Coding94th of 143 · 1416.1
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored MiniMax M1 for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where MiniMax M1 placed and give it no mark out of five.
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, which is why they get no rating.
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.
Or rent it from someone else
Cheapest of 4 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.55 in / $2.20 out
- Context served
- 1M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.55 / $2.20 | 1M | not measured | Unknown | Unknown | Unknown |
| Novita AI | $0.55 / $2.20 | 1M | not measured | Unknown | Unknown | Unknown |
| Novita AIbf16 | $0.55 / $2.20 | 1M | 71 tok/s | No | No | Confirmed |
| Minimax | $0.40 / $2.20 | 1M | 33 tok/s | No | Yesunknown period | Unknown |
Novita AIAcross the 4 listings we hold: 2 say they do not train on prompts, 0 say they do and 2 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✗ | ✗ |
| Novita AI | |||
| Novita AIbf16 | ✓ | ✗ | ✗ |
| Minimax | ✗ | ✗ | ✗ |
Tool calling: 2 of 4 listings say yes, 1 says no, 1 publishes no parameter list. JSON output: 0 of 4 listings say yes, 3 say no, 1 publishes no parameter list. Strict schema: 0 of 4 listings say yes, 3 say no, 1 publishes no parameter list.
Models people weigh against MiniMax M1
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- 1 of 4 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 4 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
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
- Modality record
- text->text
- Catalogue slug
- minimax-minimax-m1