Skip to content
LLMs
MiniMax logo

MiniMax: MiniMax M2.7

by MiniMax

MiniMax: MiniMax M2.7 is a large language model from MiniMax. It costs $0.300 per million input tokens and $1.20 per million output tokens. Its context window is 205K tokens.

ReasoningTool callingStructured outputPrompt cachingOpen weights
Input / 1M tokens
$0.300
Output / 1M tokens
$1.20
Cached input / 1M
$0.060

On repeated prefixes

Context window
205K

tokens

Who serves it cheapest

8 hosts serve MiniMax M2.7. Same weights, same API - the price difference is pure margin and routing.

Providers serving MiniMax: MiniMax M2.7, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
GMICloudCheapestfp8$0.210$0.840197K-99.5%
Mara$0.240$0.960197K-85.5%
Novitafp8$0.270$1.08205K-99.1%
AtlasCloudfp8$0.300$1.20197K-98.8%
Minimaxfp8$0.300$1.20205K-99.6%
DeepInfrafp8$0.380$1.70197K-72.8%
Groq$0.600$1.80197K-98.0%
SambaNova$0.600$2.40197K-92.1%

The spread between GMICloud and SambaNova is 2.9× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
23.2
Coding index
52.6
Agentic index
16.8

About MiniMax M2.7

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...

Specifications

MiniMax: MiniMax M2.7 specifications
Model IDminimax/minimax-m2.7
ProviderMiniMax
Context window205K tokens
Max output131K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff-
Open weightsYes - MiniMaxAI/MiniMax-M2.7
ReleasedMarch 18, 2026

Cheaper alternatives

Models that cost less than MiniMax M2.7 while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does MiniMax: MiniMax M2.7 cost?

$0.300 per million input tokens and $1.20 per million output tokens. Cached input reads cost $0.060 per million tokens.

What is the context window of MiniMax: MiniMax M2.7?

205K tokens, with up to 131K tokens of output per request.

Which provider serves MiniMax: MiniMax M2.7 cheapest?

GMICloud at $0.210 per million input tokens - 2.9× cheaper than SambaNova, the most expensive of the 8 hosts serving it.

Confirm against the source: MiniMax official pricing.