MiniMax · Released Mar 18, 2026MiniMax-M2.7-highspeed
Low-latency M2.7 variant for interactive coding plans and agent loops.
- Capability
- —No ECI score yet
- Input
- $0.60per 1M tokens
- Output
- $2.40per 1M tokens
- Context
- 205K131K max output
What it costs
- Input
- $0.60per million tokens
- Output
- $2.40per million tokens
- Cached input
- $0.06per million tokens
- Cache write
- $0.375per million tokens
- Blended (3:1)
- $1.05pricier than 57% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $2.40 |
| Team assistant25M input + 5M output tokens | $27.00 |
| Production app250M input + 50M output tokens | $270.00 |
Official MiniMax (minimax.io) API price, as listed on models.dev.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for MiniMax-M2.7-highspeed yet.
The details
- Lab
- MiniMax
- Released
- Mar 18, 2026
- Context window
- 204,800 tokens
- Max output
- 131,072 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- Always on
- Tool calling
- Yes
- Structured output
- No
- Weights
- Open weights
- API model ID
MiniMax-M2.7-highspeedon MiniMax (minimax.io)- Availability
- 14 API providerslisted on models.dev
More from MiniMax
About MiniMax-M2.7-highspeed
How much does MiniMax-M2.7-highspeed cost?
MiniMax-M2.7-highspeed costs $0.60 input / $2.40 output per million tokens (official MiniMax (minimax.io) API price). Cached input is $0.06 per million tokens, and writing to the cache costs $0.375. At a 3:1 input-to-output mix that is $1.05 per million tokens, more expensive than 57% of the 360 priced models we track.
What is the context window of MiniMax-M2.7-highspeed?
MiniMax-M2.7-highspeed accepts up to 204,800 tokens per request and can write up to 131,072 tokens in one response.
How good is MiniMax-M2.7-highspeed?
Epoch AI has not published a Capabilities Index score for MiniMax-M2.7-highspeed yet.
Is MiniMax-M2.7-highspeed open source?
Yes. MiniMax publishes the weights, so it can be downloaded and self-hosted.
What inputs does MiniMax-M2.7-highspeed support?
MiniMax-M2.7-highspeed accepts text and replies in text. It is a reasoning model, supports tool calling.
When was MiniMax-M2.7-highspeed released?
MiniMax released MiniMax-M2.7-highspeed on Mar 18, 2026.
What are the best alternatives to MiniMax-M2.7-highspeed?
The closest current models from other labs on capability, price and release date are Qwen3.5 122B-A10B (Alibaba (Qwen), $0.40 / $3.20), DeepSeek OCR 2 (DeepSeek, $0.89 / $1.47), Seed 2.0 Code (ByteDance Seed, $0.475 / $2.37) and Grok Build 0.1 (xAI, $1.00 / $2.00).