HOlO
25 signals
HOlO V1 IS LIVEone ranked AI digest a day, scored in publicREAD HOW IT WORKS →HOlO V2 STARTSyour X account, your signals, every day

Model registry / MiniMax / Minimax / MiniMax-M2.7

MiniMax-M2.7

Open MiniMax flagship for coding agents, office automation, and complex environments

Line

Minimax

Weights

Open

Released

2026-03-18

Context

205K

Input

$0.08 / 1M

Output

$0.32 / 1M

Max output

131K

Coverage

not covered yet

Overview

MiniMax-M2.7 is the open flagship model from MiniMax for coding agents, office automation, and complex environments. It is the latest in the minimax line, succeeding MiniMax-M2.5. It has a context window of 204800 tokens and a maximum output of 131072 tokens. Weights are open. It supports reasoning mode and tool calling. It accepts text and returns text. Pricing starts at $0.08 per million input tokens and $0.32 per million output tokens, with cached input at $0.017 per million tokens.

Specs

Released2026-03-18
LineMiniMax · Minimax
WeightsOpen
Context205K tokens
Max output131K tokens
Inputtext
Outputtext
ReasoningYes
Tool callingYes
Knowledge cutoffnot stated
API idMiniMax-M2.7

Pricing

Input$0.08 / 1M tokens
Cached input$0.017 / 1M tokens
Output$0.32 / 1M tokens

Against MiniMax-M2.5: input $0.15 to $0.08, output $0.88 to $0.32, cached input $0.027 to $0.017.

Range across the hosts that serve it: up to $0.819 per 1M input tokens.

Strengths

  • Open weights for self-hosting
  • 204800 token context window
  • 131072 token max output
  • Supports reasoning mode
  • Supports tool calling

Best for

  • Reach for it for coding agents
  • Reach for it for office automation
  • Reach for it for complex environments
  • Reach for it for long-context reasoning

How to access

ProviderModel id
302.AIMiniMax-M2.7
AIHubMixMiniMax-M2.7
AbacusMiniMax-M2.7
Alibaba (China)MiniMax-M2.7
Charm HyperMiniMax-M2.7
CrossModelMiniMax-M2.7
Deep InfraMiniMax-M2.7
DevPass (LLM Gateway)MiniMax-M2.7
Eden AIMiniMax-M2.7
FastRouterMiniMax-M2.7
GMI CloudMiniMax-M2.7
Hugging FaceMiniMax-M2.7

38 hosts serve this model at the price above · the maker's documentation

Minimax: every version

VersionReleasedContextInput
MiniMax-M3Current2026-06-011M$0.20
MiniMax-M2.72026-03-18205K$0.08
MiniMax-M2.52026-02-12205K$0.15
MiniMax-M2.12025-12-23205K$0.27
MiniMax-M22025-10-27205K$0.17

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

FAQ

What is the context window size?
The context window is 204800 tokens, and the maximum output is 131072 tokens.
Is MiniMax-M2.7 open weights?
Yes, the weights are open. It also supports reasoning mode and tool calling.
What is the pricing?
Input starts at $0.08 per million tokens, output at $0.32 per million tokens. Cached input is $0.017 per million tokens.
Open weightsReasoning205K context