MMiniMax · Released Oct 23, 2025
MiniMax M2
MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general…
- Released
- Oct 23 2025
- Context window
- 205K 131K out
- Input / 1M tokens
- $0.26 from $0.17
- Output / 1M tokens
- $1.02 from $1.00
Where to run it
20 providers compared
Included in MiniMax Token Plan (minimax.io), MiniMax Token Plan (minimax.cn). Cheapest: LLM Gateway, DevPass (LLM Gateway) at $0.20 / $1.00 per 1M input / output tokens — 35% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| MiniMax Token Plan (minimax.io)subscription plan | Plan | Plan | — | 205K | 131K | — | Plan |
| MiniMax Token Plan (minimax.cn)subscription plan | Plan | Plan | — | 205K | 131K | — | Plan |
| LLM Gateway | $0.20 | $1.00 | $0.03 | 197K | 131K | — | Cheapest |
| DevPass (LLM Gateway) | $0.20 | $1.00 | $0.03 | 197K | 131K | — | Cheapest |
| MinimaxFP8 | $0.26 | $1.02 | — | 205K | 131K | 100%24h | +12% |
| NanoGPTno tool calling | $0.17 | $1.53 | $0.085 | 200K | 131K | — | +27% |
| $0.30 | $1.20 | — | 197K | 177K | 84.7%24h | +31% | |
| Kilo Gateway | $0.30 | $1.20 | — | 205K | 131K | — | +31% |
| Vercel AI Gateway | $0.30 | $1.20 | $0.03 | 205K | 197K | — | +31% |
| ZenMux | $0.30 | $1.20 | $0.03 | 204K | 128K | — | +31% |
| Amazon Bedrock | $0.30 | $1.20 | — | 205K | 128K | — | +31% |
| Hugging Face | $0.30 | $1.20 | — | 205K | 131K | — | +31% |
| MiniMax (minimax.io) | $0.30 | $1.20 | — | 205K | 131K | — | +31% |
| Merge Gateway | $0.30 | $1.20 | $0.03 | 205K | 8K | — | +31% |
| Ofox | $0.30 | $1.20 | $0.03 | 205K | 131K | — | +31% |
| Eden AI | $0.30 | $1.20 | — | 205K | 131K | — | +31% |
| Qiniu | $0.30 | $1.22 | — | 200K | 128K | — | +33% |
| MiniMax (minimax.cn) | $0.31 | $1.25 | $0.031 | 205K | 131K | — | +37% |
| 302.AI | $0.33 | $1.32 | — | 1M | 128K | — | +44% |
| Cortecs | $0.35 | $1.41 | — | 400K | 196K | — | +53% |
Value
Price vs. performance
MiniMax M2 Other MiniMax Other labs Value frontier · Terminal-Bench vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
3 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| Terminal-BenchSoftware engineering · Tasks completed with the programs in a real terminal (best agent) | 30.0% | #33of 40 | GPT-5.584.7% |
| Vending-Bench 2Agents & computer use · Run a simulated vending business for a year (final balance) | $161 | #55of 61 | GPT-6 Astra$15,515 |
| WebDev ArenaDesign & visual · People vote on which model builds the better website (Elo) | 1298 | #81of 90 | Claude Opus 5.51820 |
Specs
Details
- Model ID
minimax/minimax-m2- Developer
- MiniMax
- Release date
- Oct 23, 2025 ·
- Context window
- 204,800 tokens
- Max output
- 131,072 tokens
- API price
- $0.26 / $1.02 per 1M input / output tokens
- Providers
- 20
- Input types
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.