Robots AtlasRobots Atlas
MiniMax-m2.7 Cover
Active
Mar 18, 2026
MiniMax
ProducerMiniMax
APIOpen WeightsLocal RunCloud

MiniMax M2.7

LLMReasoningTool-Using

MiniMax M2.7 is a MoE language model with 230B parameters (10B active during inference), released on March 18, 2026.

Technical specification

Context window
0K
Parameters
230B (10B active)
Max output
0K
License
MiniMax Non-Commercial License (Modified-MIT, non-commercial; commercial use requires prior written authorization)
Tools
Yes
Fine-tuning
No
Weights access
Open weights
Last updated: Apr 16, 2026

Modalities

Input
Text
Output
Text
Code

Capabilities

9

Reasoning★

Reasoning

Multi-step reasoning★

Reasoning

Long context★

Reasoning

Coding★

Coding

Function Calling

Planning

Structured output★

Structured gen.

Multilingual★

Language

Planning★

Planning

Streaming output

Reasoning

Pricing

PublicUSDper 1M tokens

MiniMax-M2.7: $0.30/M input tokens, $1.20/M output tokens (pay-as-you-go). Prompt caching read: $0.06/M tokens, prompt caching write: $0.375/M tokens. A faster 'highspeed' variant (MiniMax-M2.7-highspeed) is available at $0.60/M input and $2.40/M output.

Pricing · Calculator
Token volume10K

INPUT

$0.3000 / per 1M tokens

$0.00300

OUTPUT

$1.2000 / per 1M tokens

$0.0120

CACHE

$0.0600 / per 1M tokens

$0.00060

TOTAL

for 10K tokens

$0.0150
All plans2
TextPay as you go/ per 1M tokens
Input$0.3000
Cache$0.0600
Output$1.2000

MiniMax-M2.7 standard variant. Prompt caching write: $0.375/M tokens.

TextPay as you go/ per 1M tokens
Input$0.6000
Cache$0.0600
Output$2.4000

MiniMax-M2.7-highspeed variant. Same capability, faster inference. Prompt caching write: $0.375/M tokens.