MiniMax-M2.7
AvailableA MiniMax model with a 200K-token context window and tool calling. On the MiniMax Open Platform API since March 18, 2026.
Access details: MiniMax Open Platform API
An alias. The provider can point it at a newer version.
MiniMax-M2.7Open weights on Hugging Face: MiniMaxAI/MiniMax-M2.7
Updated Oct 1, 2026
Capabilities & limits
- Context window
- 200K
- Maximum output
- 200K
- Image input
- Unsupported
- Tool calling
- Supported
- Structured output
- Unsupported
Pricing
USD / 1M tokens- Input
- $0.30
- Output
- $1.20
Standard rates per million tokens. Discounts and long-context rates, where offered, are on MiniMax's pricing page.
Full rate card 4 rates
All prices in USD.
Input tokens
$0.30 per 1M tokens- standard
Output tokens
$1.20 per 1M tokens- standard
Cache reads
$0.06 per 1M tokens- prompt caching
Cache writes
$0.375 per 1M tokens- prompt caching
Pay-as-you-go USD.
Price history
Oct 1, 2026
Input $0.30 per million tokens
Oct 1, 2026
Output $1.20 per million tokens
Technical details
- Parameters
- Not published
- Active parameters
- Not published
- Architecture
- Not published
- Training / knowledge cutoff
- Not published
- Input modalities
- Text
- Output modalities
- Text
From MiniMax
Official announcement ↗How they describe it
Beginning the journey of recursive self-improvement
What they say is new
M2.7 is our first model deeply participating in its own evolution.
Release & lifecycle
- First available
- Mar 18, 2026
- available
- As of Oct 1, 2026