MiniMax M2
MiniMax · released Oct 22, 2025 · MiniMaxAI/MiniMax-M2
- Type
- Open weightsCustom licence
- Params
- 229B
- Context
- 205K
about 154K words of context · download allowed, licence restricts use
Our take
Written Aug 3, 2026MiniMax M2 is a 229-billion-parameter text-only model released in 2025 with a custom restricted licence. It offers broad Arena benchmark coverage across six categories and its fastest hosting is on MiniMax's own platform, though it leads no measured category.
Use this for long-context text tasks up to 204,800 tokens when the licence terms are acceptable, or when you want API access through MiniMax's own hosting for the fastest measured throughput. Skip it if you need a permissive open licence, multimodal input, or category-leading quality scores.
The case for it
- Broad benchmark coverage with consistent tracking: six distinct Arena categories measured, with multiple dated readings showing live monitoring.
- Fastest measured throughput on the cheapest provider: 31 tokens per second on MiniMax, against 16 on Google Vertex and 5 on one Novita offer.
The case against it
- No quality leadership in any measured category: Arena Text overall 1345.9, Arena Coding 1384.8, Arena Hard Prompts 1368.5, Arena Maths 1354.8 — all mid-table with no wins evident.
- Custom restricted licence, not Apache or MIT, which limits commercial freedom versus open alternatives.
- Active parameter count undisclosed, so the true inference cost per forward pass cannot be verified.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)106th of 143 · 1345.9
CodingWriting and fixing code on its own
Arena Coding105th of 143 · 1384.8
AgenticPlanning, calling tools, staying on task
MiniMax M2 is not on Arena Agent (IPS), which is where the rating would come from, so there is no rating here. It is on SWE-bench Verified, in 20th of 39 with 61.
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 M2 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 model8 scoresEvery figure we hold, from 8 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?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
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.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 5 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
- $0.26 in / $1.02 out
- Context served
- 205K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.26 / $1.02 | 205K | not measured | Unknown | Unknown | Unknown |
| Minimaxfp8 | $0.26 / $1.02 | 205K | 82 tok/s | No | Yesunknown period | Confirmed |
| Novita AI | $0.30 / $1.20 | 205K | not measured | Unknown | Unknown | Unknown |
| Novita AIfp8 | $0.30 / $1.20 | 205K | 45 tok/s | No | No | Confirmed |
| Google Vertex AI | $0.30 / $1.20 | 197K | 86 tok/s | No | No | Confirmed |
Novita AI
Google Vertex AIAcross the 5 listings we hold: 3 say they do not train on prompts, 0 say they do and 2 do not say. 3 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 | ✓ | ✓ | ✓ |
| Minimaxfp8 | ✓ | ✗ | ✗ |
| Novita AI | |||
| Novita AIfp8 | ✓ | ✓ | ✗ |
| Google Vertex AI | ✓ | ✓ | ✓ |
Tool calling: 4 of 5 listings say yes, 1 publishes no parameter list. JSON output: 3 of 5 listings say yes, 1 says no, 1 publishes no parameter list. Strict schema: 2 of 5 listings say yes, 2 say no, 1 publishes no parameter list.
Models people weigh against MiniMax M2
When we formed this view
Dates behind this page
Prices last checked 5d ago
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.
- 1 of 5 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 5 listings do not say whether they train on prompts.
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
- Architecture
- Mixture of experts
- Modality record
- text->text
- Catalogue slug
- minimax-minimax-m2