MiniMax M2.1
MiniMax 2.1 is MiniMax's latest model, optimized specifically for robustness in coding, tool use, instruction following, and long-horizon planning.
text → text · made by MiniMax
Sold by 17 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock 0 ways | $0.15per Mtok in$0.6per Mtok out | |
| AWS Bedrock cloudnot on the seller's list today | batch | $0.15per Mtok in$0.6per Mtok outpricing.us-east-1.amazonaws.com · read 2026-08-24 |
| AWS Bedrock cloud | in-region batch | $0.15per Mtok in$0.6per Mtok outpricing.us-east-1.amazonaws.com · read 2026-08-24 |
| AWS Bedrock cloud | standard | $0.3per Mtok in$1.2per Mtok outmodels.dev · read 2026-09-16 |
| AWS Bedrock cloud | in-region | $0.3per Mtok in$1.2per Mtok outpricing.us-east-1.amazonaws.com · read 2026-08-24 |
| MiniMax api | standard | $0.3per Mtok in$1.2per Mtok out$0.03per Mtok cached$0.38per Mtok cache writeplatform.minimax.io · read 2026-08-25 |
| MiniMax api | fast | $0.6per Mtok in$2.4per Mtok out$0.03per Mtok cached$0.38per Mtok cache writeplatform.minimax.io · read 2026-08-25 |
| DeepInfra aggregator | standard | $0.27per Mtok in$0.95per Mtok outapi.deepinfra.com · read 2026-08-25 |
| ElectronHub aggregator | standard | $0.3per Mtok in$1.2per Mtok outapi.electronhub.ai · read 2026-09-16 |
| Fireworks AI aggregator | standard | $0.3per Mtok in$1.2per Mtok out$0.03per Mtok cachedraw.githubusercontent.com · read 2026-09-16 |
| Hugging Face Inference Providers 2 ways | $0.3per Mtok in$1.2per Mtok out | |
| Hugging Face Inference Providers aggregator | standard | $0.3per Mtok in$1.2per Mtok outmodels.dev · read 2026-09-16 |
| Hugging Face Inference Providers aggregator | novita | $0.3per Mtok in$1.2per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Nous Research aggregator | standard | $0.3per Mtok in$1.2per Mtok out$0.03per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| Novita AI aggregator | standard | $0.3per Mtok in$1.2per Mtok out$0.03per Mtok cachedapi.novita.ai · read 2026-08-25 |
| OpenRouter 2 ways | $0.3per Mtok in$1.2per Mtok out$0.03per Mtok cached | |
| OpenRouter aggregator | standard | $0.3per Mtok in$1.2per Mtok out$0.03per Mtok cachedopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | minimax/highspeed | $0.3per Mtok in$2.4per Mtok out$0.03per Mtok cachedopenrouter.ai · read 2026-08-25 |
| Vercel AI Gateway aggregator | standard | $0.3per Mtok in$1.2per Mtok out$0.03per Mtok cached$0.38per Mtok cache writeai-gateway.vercel.sh · read 2026-08-25 |
| PPIO aggregator | standard | $2.1per Mtok in$8.4per Mtok outapi.ppinfra.com · read 2026-09-16 |
Measured 15 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 6thof 262 | MMLU-Pro | Overall (accuracy) | 88 |
| 14thof 25 | SWE-Bench Pro (Public Dataset) | Resolve Rate | 36.81 |
| 61stof 150 | Design Arena · uicomponent (models) | Elo | 1238 |
| 65thof 152 | Design Arena · dataviz (models) | Elo | 1222 |
| 69thof 109 | Design Arena · svg (models) | Elo | 1156 |
| 70thof 147 | Design Arena · 3d (models) | Elo | 1193 |
| 70thof 156 | Design Arena · codecategories (models) | Elo | 1206 |
| 70thof 162 | Design Arena · website (models) | Elo | 1214 |
| 75thof 105 | Vectara Hallucination Leaderboard | Hallucination Rate | 11.8 |
| 80thof 112 | Ale bench — Epoch AI | Performance | 623.83 |
| 81stof 121 | Webdev arena — Epoch AI | Arena Score | 1386.99 |
| 82ndof 128 | LMArena · WebDev | Score (Elo) | 1387 |
| 96thof 155 | Design Arena · gamedev (models) | Elo | 1157 |
| 113thof 202 | Terminalbench — Epoch AI | Accuracy mean | 0.366 |
| 170thof 402 | LMArena · Text | Score (Elo) | 1384 |
About
MiniMax M2.1 — a text model from MiniMax, sold by 11 companies from $0.27 in and $0.95 out per million tokens, placed 6th of 262 on MMLU-Pro.
It takes text and returns text, with a context window of 204,800 tokens. It was published in December 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning and code. Eleven companies sell it. The cheapest is $0.27 in and $0.95 out per million tokens at DeepInfra. Beside the standard rate there are regional, batch, separately routed and faster lanes. It has been measured on 15 boards, and stands best at 6th of 262 on MMLU-Pro.
Every current figure
- Maker
- MiniMax
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 204,800 tokens
- Longest answer
- 196,000 tokens
- Published
- December 2025
- Parameters
- 229 billion
- Licence
- not read
- Sellers
- 11
- Price
- $0.27 in and $0.95 out per million tokens — DeepInfra
- Boards
- 15
- Best place
- 6th of 262 — MMLU-Pro
Known as 5 names
MiniMax-M2.1minimax-2.1MiniMaxAI/MiniMax-M2.1MiniMax-M2.1-highspeedminimax/minimax-m2.1