MMiniMax · Released Mar 18, 2026
MiniMax M2.7
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through…
- Top 48%SciCode
- Top 50%Terminal-Bench
- Released
- Mar 18 2026
- Context window
- 205K 131K out
- Input / 1M tokens
- $0.30 from Free
- Output / 1M tokens
- $1.20 from Free
Where to run it
47 providers compared
Free to try on UnoRouter, AIHubMix — free endpoints are often limited-time and rate-limited. Included in MiniMax Token Plan (minimax.io), SCNet Token Plan, MiniMax Token Plan (minimax.cn), OpenCode Go. Cheapest: LLM Gateway, DevPass (LLM Gateway) at $0.08 / $0.32 per 1M input / output tokens — 90% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| UnoRouterfree · may be limited-time | Free | Free | — | 205K | 131K | — | Free |
| AIHubMixfree · may be limited-time | Free | Free | — | 205K | 128K | — | Free |
| MiniMax Token Plan (minimax.io)subscription plan | Plan | Plan | Plan | 205K | 131K | — | Plan |
| SCNet Token Plansubscription plan | Plan | Plan | Plan | 205K | 131K | — | Plan |
| MiniMax Token Plan (minimax.cn)subscription plan | Plan | Plan | Plan | 205K | 131K | — | Plan |
| OpenCode Gosubscription plan | Plan | Plan | Plan | 205K | 131K | — | Plan |
| LLM Gateway | $0.08 | $0.32 | $0.017 | 205K | 131K | — | Cheapest |
| DevPass (LLM Gateway) | $0.08 | $0.32 | $0.017 | 205K | 131K | — | Cheapest |
| AIHubMix | $0.20 | $0.20 | — | 205K | 128K | — | +43% |
| EmpirioLabs AI | $0.15 | $0.60 | $0.03 | 200K | 33K | — | +87% |
| GMICloudFP8 | $0.21 | $0.84 | $0.042 | 197K | 177K | 99%24h | +162% |
| NanoGPT | $0.21 | $0.84 | $0.042 | 205K | 131K | — | +162% |
| Deep Infra | $0.25 | $1.00 | $0.05 | 197K | 131K | — | +212% |
| NovitaFP8 | $0.27 | $1.08 | $0.054 | 205K | 131K | 99.3%24h | +238% |
| Pioneer | $0.28 | $1.20 | $0.28 | 205K | 131K | — | +264% |
| Moark | $0.29 | $1.20 | — | 205K | 131K | — | +270% |
| MinimaxFP8 | $0.30 | $1.20 | $0.06 | 205K | 131K | 99.9%24h | +275% |
| AtlasCloudFP8 | $0.30 | $1.20 | $0.06 | 197K | 177K | 98.8%24h | +275% |
| FrogBot | $0.30 | $1.20 | $0.06 | 192K | 8K | — | +275% |
| Kilo Gateway | $0.30 | $1.20 | $0.06 | 205K | 131K | — | +275% |
| Vercel AI Gateway | $0.30 | $1.20 | $0.06 | 205K | 131K | — | +275% |
| Together AI | $0.30 | $1.20 | $0.06 | 197K | 131K | — | +275% |
| Requesty | $0.30 | $1.20 | $0.06 | 200K | 128K | — | +275% |
| FastRouter | $0.30 | $1.20 | $0.06 | 205K | 131K | — | +275% |
| 302.AI | $0.30 | $1.20 | — | 205K | 131K | — | +275% |
| ZenMux | $0.30 | $1.20 | $0.06 | 205K | 131K | — | +275% |
| Auriko | $0.30 | $1.20 | $0.06 | 205K | 131K | — | +275% |
| Novita AI | $0.30 | $1.20 | $0.06 | 205K | 131K | — | +275% |
| Abacus | $0.30 | $1.20 | — | 205K | 131K | — | +275% |
| Tempr Gateway | $0.30 | $1.20 | $0.06 | 205K | 131K | — | +275% |
| Hugging Face | $0.30 | $1.20 | $0.06 | 205K | 131K | — | +275% |
| Ollama Cloud | $0.30 | $1.20 | $0.06 | 197K | 197K | — | +275% |
| MiniMax (minimax.io) | $0.30 | $1.20 | $0.06 | 205K | 131K | — | +275% |
| CommandCode | $0.30 | $1.20 | $0.06 | 200K | 131K | — | +275% |
| Merge Gateway | $0.30 | $1.20 | $0.06 | 205K | 8K | — | +275% |
| Ofox | $0.30 | $1.20 | $0.06 | 205K | 131K | — | +275% |
| OrcaRouter | $0.30 | $1.20 | $0.06 | 205K | 131K | — | +275% |
| OpenCode | $0.30 | $1.20 | $0.06 | 205K | 131K | — | +275% |
| Alibaba (China) | $0.30 | $1.20 | $0.06 | 205K | 131K | — | +275% |
| Eden AI | $0.30 | $1.20 | $0.06 | 205K | 131K | — | +275% |
| MiniMax (minimax.cn) | $0.31 | $1.25 | $0.063 | 205K | 131K | — | +292% |
| CrossModel | $0.33 | $1.32 | $0.066 | 205K | 131K | — | +313% |
| Kenari | $0.36 | $1.43 | $0.069 | 205K | 131K | — | +348% |
| Venice AI | $0.38 | $1.50 | $0.069 | 198K | 33K | — | +369% |
| SCX.ai | $0.48 | $1.79 | $0.05 | 197K | 197K | — | +477% |
| Charm Hyper | $0.48 | $1.85 | $0.24 | 262K | 7K | — | +490% |
| Groq | $0.60 | $1.80 | — | 197K | 131K | 98.9%24h | +543% |
| Minimaxhighspeed · FP8 | $0.60 | $2.40 | $0.06 | 205K | 131K | 98.4%24h | +650% |
| Opper | $0.70 | $2.79 | — | 197K | 131K | — | +771% |
| UnoRouter | $0.82 | $3.28 | — | 205K | 131K | — | +924% |
Value
Price vs. performance
MiniMax M2.7 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
7 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| Terminal-BenchSoftware engineering · Tasks completed with the programs in a real terminal (best agent) | 45.1% | #20of 40 | GPT-5.584.7% |
| GBAEvalSoftware engineering · Build a Game Boy Advance emulator from scratch | 0.0% | #22of 23 | Claude Opus 579.6% |
| SciCodeSoftware engineering · Research-coding problems from the natural sciences | 50.1% | #48of 102 | Claude Opus 5.566.9% |
| WebDev ArenaDesign & visual · People vote on which model builds the better website (Elo) | 1398 | #62of 90 | Claude Opus 5.51820 |
| ExploitBenchCybersecurity · Exploit real, hardened security vulnerabilities | 13.3% | #8of 8 | GPT-5.547.4% |
| CritPtReasoning & knowledge · Open-ended, research-level physics problems | 0.6% | #86of 111 | GPT-5.6 Sol32.3% |
| ProofBenchMaths · Graduate maths proofs verified in Lean 4 | 3.0% | #70of 70 | Claude Sonnet 5.5100.0% |
Specs
Details
- Model ID
minimax/minimax-m2.7- Developer
- MiniMax
- Release date
- Mar 18, 2026 ·
- Context window
- 204,800 tokens
- Max output
- 131,072 tokens
- API price
- $0.30 / $1.20 per 1M input / output tokens
- Providers
- 47
- 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.