MiniMax M2.7
MiniMax · released Apr 9, 2026 · MiniMaxAI/MiniMax-M2.7
- 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 M2.7 is a dense text model with a 204,800-token request limit and a restricted licence. Its coding score is the standout measured skill, while its overall agent performance sits below the field midpoint.
Choose this for coding-heavy workflows where its Arena Coding score is the anchor, or for long-context text work at 204,800 tokens. It suits budget inference with strong throughput from one tracked host. Skip it if you need permissive licensing, robust agentic behaviour, or multimodal input.
The case for it
- Strongest measured skill is coding — 64 points above its own overall text score.
- Best price-throughput pairing among tracked offers, with one host undercutting the vendor's own pricing while delivering more than double the speed.
- Only positive agent sub-score is tool use, the lone bright spot in an otherwise negative agent profile.
The case against it
- Overall agent performance is below the field midpoint, with negative scores on recovery, task outcome and steerability.
- Custom restricted licence — not Apache 2.0 or MIT — with constrained commercial and redistribution terms.
- Wide throughput variance at identical price points: one host delivers less than a fifth of the speed another manages for the same rate.
How good is it?
An open text model for chat and code, though multi-step tasks and course changes are where it struggles.
- carrying out multi-step tasks for youArena Agent · 50th of 55
- changing course when you give new instructionsArena Agent · Steerability · 44th of 55
- getting back on track after a step failsArena Agent · Recovery · 50th of 55
EverydayGeneral questions and everyday reasoning
Arena Text (overall)83rd of 168 · 1415
CodingWriting and fixing code on its own
Arena Coding70th of 168 · 1480
AgenticPlanning, calling tools, staying on task
Arena Agent50th of 55 · −0.14
Arena Agent is the only board that has scored it for this.
WritingDrafting and rewriting prose
Arena Creative Writing94th of 168 · 1363
Arena Creative Writing is the only board that has scored it for this.
Placings on Arena's agent boards, from live sessions people ran themselves. A model can lead on one of these and sit mid-field on the others.
Boards this model appears on that none of the ratings above are built on.
Every published score for this model12 scoresEvery figure we hold, from 12 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. 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 between 1 hour and 28 days ago — each listing carries its own date.
Some hosts sell this model at two prices: on their own price list (“direct”) and on their OpenRouter listing (“through OpenRouter”). Where the two differ, the row shows both, each with the date we last read it.
- per 1M tokens
- $0.21 in / $0.84 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 | $0.21 / $0.84checked 1 hour ago | 205K | not measured | Unknown | Unknown | Unknown |
| GMICloudfp8Through OpenRouter | $0.21 / $0.84checked 1 hour ago | 197K177K max reply | 22 tok/s | No | Yesunknown period | Unknown |
| MaraThrough OpenRouter | $0.24 / $0.96checked 43 hours ago | 197K177K max reply | 66 tok/s | No | No | Confirmed |
| DeepInfrafp8Direct | $0.25 / $1.00checked 28 days ago | 197K | not measured | Unknown | Unknown | Unknown |
| Novita AIfp8Direct and through OpenRouter | $0.30 / $1.20directchecked 1 hour ago$0.27 / $1.08through OpenRouterchecked 1 hour ago | 205K131K max reply through OpenRouter | 14 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| AtlasCloudfp8Through OpenRouter | $0.30 / $1.20checked 1 hour ago | 197K177K max reply | 19 tok/s | No | Yesunknown period | Unknown |
| Minimaxfp8Through OpenRouter | $0.30 / $1.20checked 1 hour ago | 205K131K max reply | 51 tok/s | No | Yesunknown period | Confirmed |
| GroqThrough OpenRouter | $0.60 / $1.80checked 1 hour ago | 197K131K max reply | 309 tok/s | No | No | Confirmed |
| SambaNovaDirect and through OpenRouter | $0.60 / $2.40checked 25 hours ago directchecked 7 hours ago through OpenRouter | 197K177K max reply through OpenRouter | 14 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Minimaxhighspeed tierfp8Through OpenRouter | $0.60 / $2.40checked 1 hour ago | 205K131K max reply | 32 tok/s | No | Yesunknown period | Unknown |
DeepInfra
Novita AI
Groq
SambaNovaAcross the 10 listings we hold: 8 say they do not train on prompts (2 of them only through OpenRouter), 0 say they do and 2 do not say. 5 appear in the zero-retention registry we check (2 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 | ✓ | ✓ | ✓ |
| GMICloudfp8Through OpenRouter | ✓ | ✓ | ✗ |
| MaraThrough OpenRouter | ✓ | ✓ | ✓ |
| DeepInfrafp8Direct | |||
| Novita AIfp8Direct and through OpenRouter | ✓ | ✓ | ✗ |
| AtlasCloudfp8Through OpenRouter | ✓ | ✓ | ✗ |
| Minimaxfp8Through OpenRouter | ✓ | ✓ | ✗ |
| GroqThrough OpenRouter | ✓ | ✗ | ✗ |
| SambaNovaDirect and through OpenRouter | ✓ | ✗ | ✗ |
| Minimaxhighspeed · fp8Through OpenRouter | ✓ | ✓ | ✗ |
Tool calling: 9 of 10 listings say yes, 1 publishes no parameter list. JSON output: 7 of 10 listings say yes, 2 say no, 1 publishes no parameter list. Strict schema: 2 of 10 listings say yes, 7 say no, 1 publishes no parameter list.
Models people weigh against MiniMax M2.7
When we formed this view
Recent changes
Each 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.
- 1 of 10 listings publishes no parameter list, so what its API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 10 listings do not say whether they train on prompts, and 2 answer only through OpenRouter, not for their 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-M2.7
- Architecture
- Mixture of experts
- Takes in, gives back
- Text in, text out
- Catalogue slug
- minimax-minimax-m2-7