MMiniMax · Released Feb 12, 2026
MiniMax M2.5
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
- Released
- Feb 12 2026
- Context window
- 205K 33K out
- Input / 1M tokens
- $0.27
- Output / 1M tokens
- $0.95
Where to run it
8 providers compared
Cheapest: Venice at $0.27 / $0.95 per 1M input / output tokens — 58% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Venice | $0.27 | $0.95 | $0.03 | 198K | 33K | 94.8%24h | Cheapest |
| StreamLake | $0.27 | $1.08 | $0.027 | 200K | 128K | 99.8%24h | +7% |
| AtlasCloudFP8 | $0.29 | $1.20 | $0.06 | 197K | 177K | 99.2%24h | +18% |
| DigitalOcean | $0.30 | $1.20 | $0.06 | 66K | 59K | 100%24h | +19% |
| Friendli | $0.30 | $1.20 | $0.06 | 197K | 177K | 100%24h | +19% |
| NovitaFP8 | $0.30 | $1.20 | $0.03 | 205K | 131K | 100%24h | +19% |
| MinimaxFP8 | $0.30 | $1.20 | $0.03 | 205K | 131K | 100%24h | +19% |
| GMICloudFP8 | $0.30 | $1.20 | $0.03 | 197K | 177K | 96%24h | +19% |
| Minimaxhighspeed · FP8 | $0.60 | $2.40 | $0.06 | 205K | 131K | 93.6%24h | +139% |
Value
Price vs. performance
MiniMax M2.5 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
6 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| Terminal-BenchSoftware engineering · Tasks completed with the programs in a real terminal (best agent) | 42.7% | #22of 40 | GPT-5.584.7% |
| Vending-Bench 2Agents & computer use · Run a simulated vending business for a year (final balance) | $-23 | #60of 61 | GPT-6 Astra$15,515 |
| WebDev ArenaDesign & visual · People vote on which model builds the better website (Elo) | 1384 | #68of 88 | Claude Opus 5.51820 |
| ARC-AGI-2Reasoning & knowledge · Few-shot abstract reasoning on grid puzzles | 4.9% | #53of 63 | GPT-6 Astra95.0% |
| ARC-AGI-1Reasoning & knowledge · Pattern induction from input–output examples | 63.7% | #49of 63 | Gemini 4 Argon98.5% |
| ProofBenchMaths · Graduate maths proofs verified in Lean 4 | 4.0% | #69of 70 | Claude Sonnet 5.5100.0% |
Specs
Details
- Model ID
minimax/minimax-m2.5- Developer
- MiniMax
- Release date
- Feb 12, 2026 ·
- Context window
- 204,800 tokens
- Max output
- 32,768 tokens
- API price
- $0.27 / $0.95 per 1M input / output tokens
- Providers
- 8
- Input types
- text
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date, prices and providers from OpenRouter's catalog; buying directly from a provider can cost a little differently. 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.