Identity
- Status
- active
- Developer ID
MiniMaxAI/MiniMax-M2.7- Released
- Mar 18, 2026
- Version
- MiniMax-M2.7
- License
- other
MiniMaxM2.7
MiniMax-M2.7 is an open-weight language model published by MiniMax.
- Token context
- 205K tokens
- Inputs
- Text
- Outputs
- Text
- Released
- Mar 18, 2026
Providers & Pricing
Estimate workload cost →| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
 DeepinfraAvailable | $0.25 | $1.00 | $0.050 | — | Sep 3, 2026 | Provider-reported |
 OpenrouterAvailable | $0.30 | $1.20 | $0.060 | — | Aug 28, 2026 | Provider-reported |
Benchmarks
All benchmark results →| LMArena Text Arenatext-2026-10-15-a64ca3b12b6e | 1,404.83 | — | 84,977 | minimax-m2.7; 95% CI [1401.50702597, 1408.15721867]; votes 84977; rank 148unknown | Original sourcewinner eligible | Third-party benchmark |
At a Glance
Model Facts
Capacity
- Token context
- 205K tokens
- Maximum output
- Unknown
- Total parameters
- 228.7B
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text
- Outputs
- Text
- API available
- Yes
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- No
- Vision
- No
- Tool calling
- Yes
- Capabilities
- chat, generation, tools
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
AliasesMiniMaxAI/MiniMax-M2.7, MiniMaxAI/MiniMax-M2.7
Explicit Unknowns
- Maximum output
- Knowledge cutoff
Primary Evidence
Sources and Observation Date
MiniMaxAI/MiniMax-M2.7 developer model repositoryMiniMax · observed Aug 28, 2026Deepinfra catalogDeepinfra · observed Oct 19, 2026OpenRouter minimax/minimax-m2.7 model APIOpenRouter · observed Aug 28, 2026MiniMaxAI/MiniMax-M2.7 Hugging Face inference-provider mappingHugging Face · observed Aug 28, 2026MiniMaxAI/MiniMax-M2.7 config.json at d494266a4affMiniMax · observed Aug 28, 2026MiniMaxAI/MiniMax-M2.7 immutable Hub API metadataMiniMax · observed Aug 28, 2026MiniMax M2.7: Early Echoes of Self-EvolutionMiniMax · observed Aug 28, 2026MiniMaxAI/MiniMax-M2.7 tokenizer_config.json at d494266a4affMiniMax · observed Aug 28, 2026Fireworks Ai catalogFireworks Ai · observed Oct 19, 2026Hugging Face catalogHugging Face · observed Sep 2, 2026Together Ai catalogTogether Ai · observed Oct 19, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
MiniMax M2.7MiniMax | vs | MiniMax M3MiniMax | family variantstext |
MiniMax M2.7MiniMax | vs | cross-developer peerstext | |
MiniMax M2.7MiniMax | vs | cross-developer peerstext | |
MiniMax M2.7MiniMax | vs | MiniMax M2.5MiniMax | family variantstext |
MiniMax M2.7MiniMax | vs |  Codestral 22B v0.1Mistral AI | cross-developer peerstext |
MiniMax M2.7MiniMax | vs | Devstral 2 123B Instruct 2512Mistral AI | cross-developer peerstext |
MiniMax M2.7MiniMax | vs |  Kimi K2 InstructMoonshot AI | cross-developer peerstext |
MiniMax M2.7MiniMax | vs | cross-developer peerstext | |
MiniMax M2.7MiniMax | vs |  Qwen3 Coder NextQwen | cross-developer peerstext |
MiniMax M2.7MiniMax | vs | cross-developer peerstext | |
MiniMax M2.7MiniMax | vs | cross-developer peerstext | |
MiniMax M2.7MiniMax | vs |  Hy3Tencent | cross-developer peerstext |
Questions
MiniMax M2.7 FAQs
What is MiniMax M2.7?+
MiniMax-M2.7 is an open-weight language model published by MiniMax. It is developed by MiniMax and its current sourced lifecycle status is active.
What inputs and outputs does MiniMax M2.7 support?+
MiniMax M2.7's current record lists Text as input and Text as output.
How much context does MiniMax M2.7 support?+
The current record lists a 205K-token context window and does not report a maximum output length.
Is MiniMax M2.7 available through an API?+
MiniMax M2.7 is marked as API-available. The directly sourced provider records currently include Deepinfra, Fireworks Ai, Hugging Face, Openrouter, and Together Ai.
How large is MiniMax M2.7?+
The current record lists 228.7B total parameters and an unknown active parameter count. Its architecture is MiniMaxM2ForCausalLM.
What capabilities and tasks does MiniMax M2.7 support?+
MiniMax M2.7's recorded capabilities are chat, generation, and tools. Its supported tasks are text.
How much does MiniMax M2.7 cost through an API?+
The lowest directly sourced prices currently attached to MiniMax M2.7 are $0.25 per million input tokens through Deepinfra and $1.00 per million output tokens through Deepinfra. Prices are provider-specific and should be checked against each cited observation date.
Can MiniMax M2.7 be self-hosted?+
MiniMax M2.7 is an open-weight model. Self-hosting is supported, and the recorded license is other.
Does MiniMax M2.7 have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are MiniMaxAI/MiniMax-M2.7.
Which models can MiniMax M2.7 be compared with?+
The current compatible peer set includes MiniMax M3, Command A Plus 05 2026 BF16, Llama 3.1 405B Instruct, MiniMax M2.5, and Codestral 22B v0.1. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →