MiniMax-M2.7
Summary
MiniMax-M2.7 is an open-weight language model from MiniMax, released on 18 Mar 2026. It accepts text and generates text, with a 205K-token context window and up to 131K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.21 per million input tokens and $0.84 per million output tokens (OpenRouter), across 4 providers we track. It is scheduled for retirement on 5 Nov 2026.
Open MiniMax flagship for coding agents, office automation, and complex environments
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | MiniMax |
|---|---|
| Release date | 18 Mar 2026 [models.dev] |
| Status | Deprecated [models.dev] |
| Weights | Open weights [Hugging Face] |
| Parameters | 229B [Hugging Face] |
| Context window | 205K (204,800 tokens) [models.dev] |
| Max output | 131K tokens [models.dev] |
| Knowledge cutoff | Jan 2025 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Retirement date | 5 Nov 2026 [OpenRouter] |
| Hugging Face | MiniMaxAI/MiniMax-M2.7 [Hugging Face] |
MiniMax-M2.7 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| OpenRouter minimax/minimax-m2.7 | $0.21 | $0.84 | $0.04 | 197K | OpenRouter, 18 Nov 2026 |
| Hugging Face Inference Providers MiniMaxAI/MiniMax-M2.7 | $0.30 | $1.20 | $0.06 | 205K | models.dev, 18 Nov 2026 |
| Novita AI minimax/minimax-m2.7 | $0.30 | $1.20 | $0.06 | 205K | models.dev, 18 Nov 2026 |
| Vercel AI Gateway minimax/minimax-m2.7 | $0.30 | $1.20 | $0.06 | 197K | models.dev, 18 Nov 2026 |
Running MiniMax-M2.7 locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 139 GB | 142 GB | 148 GB |
| Q8_0 (8-bit) | 243 GB | 246 GB | 252 GB |
| FP16 / BF16 (16-bit) | 457 GB | 460 GB | 467 GB |
At 4-bit with an 8K conversation, MiniMax-M2.7 needs about 142 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.
Frequently asked questions
What is the context window of MiniMax-M2.7?
MiniMax-M2.7 has a context window of 204,800 tokens (205K) and can generate up to 131,072 tokens in a single response, according to models.dev.
How much does the MiniMax-M2.7 API cost?
MiniMax-M2.7 is listed from $0.21 per million input tokens and $0.84 per million output tokens (OpenRouter). Prices last verified 18 Nov 2026.
Is MiniMax-M2.7 open source?
MiniMax-M2.7 is an open-weight model: its weights are published on Hugging Face as MiniMaxAI/MiniMax-M2.7. Check the license terms before commercial use.
When was MiniMax-M2.7 released?
MiniMax released MiniMax-M2.7 on 18 Mar 2026, according to models.dev.
Which providers offer MiniMax-M2.7?
We track MiniMax-M2.7 on 4 providers: OpenRouter, Hugging Face Inference Providers, Novita AI, Vercel AI Gateway.
How much VRAM does MiniMax-M2.7 need?
About 142 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 246 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Qwen3.5 35B-A3B | Alibaba (Qwen) | 23 Feb 2026 | 262K | $0.14 | $1 | Open |
| Qwen3.6 35B-A3B | Alibaba (Qwen) | 17 Apr 2026 | 262K | $0.10 | $0.90 | Open |
| Mistral Small 4 | Mistral AI | 16 Mar 2026 | 262K | $0.15 | $0.60 | Open |
| Hy3 preview | Tencent (Hunyuan) | 20 Apr 2026 | 262K | $0.18 | $0.60 | Open |
| Step 3.7 Flash | StepFun | 29 May 2026 | 256K | $0.20 | $1.15 | Open |
| Gemma 4 31B IT | Google DeepMind | 2 Apr 2026 | 262K | $0.14 | $0.40 | Open |
Change history
- Knowledge cutoff changed from 1 Jan 2025 to Jan 2025
- Knowledge cutoff changed from Jan 2025 to 1 Jan 2025
- Knowledge cutoff changed from Sept 2024 to Jan 2025
- Knowledge cutoff changed from 1 Jan 2025 to Sept 2024
- Knowledge cutoff changed from Jan 2025 to 1 Jan 2025
- Knowledge cutoff changed from Sept 2024 to Jan 2025
- Knowledge cutoff changed from Jan 2025 to Sept 2024
- Knowledge cutoff changed from Sept 2024 to Jan 2025
- OpenRouter price changed: input $0.30 → $0.21, output $1.20 → $0.84 per 1M tokens
- Knowledge cutoff changed from 1 Jan 2025 to Sept 2024
- Retirement date changed from none to 5 Nov 2026
- Knowledge cutoff changed from Jan 2025 to 1 Jan 2025
- Knowledge cutoff changed from Sept 2024 to Jan 2025
- Knowledge cutoff changed from Jan 2025 to Sept 2024
- Knowledge cutoff changed from Sept 2024 to Jan 2025
- Knowledge cutoff changed from 1 Jan 2025 to Sept 2024
- Knowledge cutoff changed from Sept 2024 to 1 Jan 2025
- Knowledge cutoff changed from 1 Jan 2025 to Sept 2024
- Knowledge cutoff changed from Sept 2024 to 1 Jan 2025
- No longer listed on togetherai
- Status changed from active to deprecated
- No longer listed on minimax
- Knowledge cutoff changed from 1 Jan 2025 to Sept 2024
- OpenRouter price changed: input $0.21 → $0.30, output $0.84 → $1.20 per 1M tokens
Sources
- https://openrouter.ai/minimax/minimax-m2.7
- https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M2.7.toml
- https://huggingface.co/MiniMaxAI/MiniMax-M2.7
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/MiniMaxAI/MiniMax-M2.7.toml
- https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/minimax/minimax-m2.7.toml
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/minimax/minimax-m2.7.toml