MiniMax-M2.5
by MiniMaxChat
Prior MiniMax coding model for agent workflows, office edits, and automation
- Context
- 205K tokens
- Max output
- 131,072 tokens
- Parameters
- 229B total, 10B active
- Released
- 2026-02-12
- Weights
- Open
- Licence
- modified-mit
minimax/minimax-m2-5 · also seen as MiniMaxAI/MiniMax-M2.5, minimax-m25, public/minimax-m25, novita/minimax-m2.5, +15 more
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2026-02-12
- Weights
- Opennot gated
- License
- modified-mit
- Input
- Text
- Output
- Text
- Context window
- 204,800 max across endpoints
- Max output
- 131,072
- Providers
- 37 + 17 gateways, not counted as providers
- Epoch Capabilities Index
- 146.7 ± 2.7 against price
- Direct price range
- $0.194–$0.300 in · $0.88–$1.22 out per 1M tokens · 25 of 37 providers have a comparable price
More details
- Last updated
- 2026-06-15
- Knowledge cutoff
- 2025-08
- Weights link
- Hugging Face · MiniMaxAI/MiniMax-M2.5
- Parameters
- 229B total, 10B active
- Developer country
- China
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel tools
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt caching
- Web searchunknown
- Computer useunknown
- System messages
- Assistant prefillunknown
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
Atom feedNo change since 19 Oct 2026. The cheapest direct price has been $0.22 in / $0.88 out per 1M tokens at DInference on every data refresh since then.
Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs MiniMax-M2.5 |
|---|---|---|---|---|---|
| Mercury Coder Small BetaInception | $0.375 | $0.25 | $1.00 | 32.8K | −2% cheaper |
| GPT-5.4 nanoOpenAI | $0.375 | $0.20 | $1.25 | 400K | −2% cheaper |
| Perceptron Mk1perceptron | $0.375 | $0.15 | $1.50 | 32.8K | −2% cheaper |
| Perceptron Mk1.5perceptron | $0.375 | $0.15 | $1.50 | 36.9K | −2% cheaper |
| Beam 1.0 501B A23BReflection | $0.375 | $0.25 | $1.00 | 1.05M | −2% cheaper |
| MiniMax-M2MiniMax | $0.397 | $0.17 | $1.53 | 205K | +3% |
| Toast 1Mixedbread | $0.37 | $0.30 | $0.72 | 131K | −3% cheaper |
| DeepSeek V3.1DeepSeek | $0.367 | $0.25 | $0.95 | 164K | −4% cheaper |
More from MiniMax
Newest MiniMax models in the catalogue. All MiniMax models
| Model | Released | Context | Listed price |
|---|---|---|---|
| MiniMax-M3.1-Flash | 2026-10-19 | 1M | from $0.15 |
| MiniMax-M3.1-Flash-Preview | 2026-09-27 | 1M | unpriced |
| H3 Max | 2026-09-02 | — | unpriced |
| MiniMax H3 Max | 2026-08-27 | — | unpriced |
| MiniMax H3 | 2026-07-31 | — | unpriced |
| H3 | 2026-07-29 | — | unpriced |
| Speech 2.8 Turbo | 2026-07-16 | — | unpriced |
| Speech 2.8 HD | 2026-07-16 | — | unpriced |