China AI Hub
Models / MiniMax-M2.7-Highspeed
MiniMax-M2.7-Highspeed
MiniMax M2.7 family · Provider: minimax · Status: active · Released: 2026-03-18
MiniMax-M2.7-Highspeed is a MiniMax M2.7 model developed by minimax, a Chinese AI company headquartered in Room 1704-1, No. 1699 Gubei Road, Minhang District, Shanghai, China, released 2026-03-18 with a 204,800-token context window and open weights.
| Key fact | Value |
|---|---|
| Model ID | minimax-m2.7-highspeed |
| Architecture | Not publicly disclosed |
| Context window | 204,800 tokens |
| Open weights | Yes |
| License | Custom NON-COMMERCIAL license (MIT-style terms for non-commercial use only; any commercial use requires prior written authorization from MiniMax at api@minimax.io; attribution 'Built with MiniMax M2.7' required) |
| Self-hosting | Yes |
| API available | Yes |
| API pricing | $0.6 input / $2.4 output per 1M tokens (USD) · provider pricing page |
| Regions | china, international |
| Cloud providers | MiniMax Platform |
Capabilities
| Capability | Supported |
|---|---|
| Reasoning | Yes |
| Coding | Unknown |
| Math | Unknown |
| Chinese | Unknown |
| English | Unknown |
| Multilingual | Unknown |
| Vision | No |
| Audio | Unknown |
| Video | Unknown |
| Tool calling | Yes |
| Function calling | Unknown |
| Structured output | Unknown |
| Agent capability | Unknown |
| RAG | Unknown |
| Computer use | Unknown |
Known limitations
- Text-only input; interleaved thinking always on (cannot be disabled via API)
- Must echo full assistant content (thinking blocks) back in multi-turn history
MiniMax-M2.7-Highspeed is the same model as MiniMax-M2.7 served at higher throughput (~100 tokens/s, vendor claim, “same quality, faster”). International pricing is 2x the standard tier: $0.60 input / $2.40 output per 1M tokens, cache reads $0.06 (as of 2026-09-20).
Provider
Pricing
Agents built on this model
Related models (same family)
API
Model family timeline
| Model | Released | Status |
|---|---|---|
| MiniMax-M2.7-Highspeed (this page) | 2026-03-18 | active |
| MiniMax-M2.7 | 2026-03-18 | active |
Data interpretation
| Field | Value | Evidence type |
|---|---|---|
| Context window | 204,800 tokens | Official |
| Open weights | Yes | Official |
| License | Custom NON-COMMERCIAL license (MIT-style terms for non-commercial use only; any commercial use requires prior written authorization from MiniMax at api@minimax.io; attribution 'Built with MiniMax M2.7' required) | Official |
| API pricing | $0.6 / $2.4 per 1M tokens (USD) | Official |
| Family position | 2 models in the MiniMax M2.7 family | China AI Hub analysis |
Evidence types: Official = vendor documentation, pricing pages or model cards. Vendor-reported = benchmark scores published by the vendor. China AI Hub analysis = derived from the database itself. See the sourcing policy.
Sources
Confidence and source hierarchy per the sourcing policy. Facts change; check the source before relying on this page.
What is the context window of MiniMax-M2.7-Highspeed?
MiniMax-M2.7-Highspeed has a 204,800-token context window.
Is MiniMax-M2.7-Highspeed open weight?
Yes — MiniMax-M2.7-Highspeed weights are openly available under the Custom NON-COMMERCIAL license (MIT-style terms for non-commercial use only; any commercial use requires prior written authorization from MiniMax at api@minimax.io; attribution 'Built with MiniMax M2.7' required) license.
How much does MiniMax-M2.7-Highspeed cost through the API?
$0.6 per 1M input tokens and $2.4 per 1M output tokens (USD).
Where does China AI Hub get its MiniMax-M2.7-Highspeed data?
From 2 sources (official pages first), last verified 2026-09-20. Benchmark scores are labeled by source type; see the sourcing policy for details.