MiniMax

MiniMax M2

minimax/minimax-m2

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

MiniMax M2

reasoning open weights tools

MiniMax minimax/minimax-m2

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...

Input $/1M: $0.26
Output $/1M: $1.02
Context: 205K
Max output: 131K
Released: Oct 23, 2025
Modalities: text

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs MiniMax M2
targets:
  - id: minimax-m2
    kind: llm
    name: MiniMax M2
    metadata:
      model: minimax/minimax-m2          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 204800
    cost:
      usd_per_1k_tokens: 0.000637

Price among MiniMax models

Input list price per million tokens; MiniMax M2 is the 2nd cheapest of 9 listed.

1
MiniMax-01
$0.20
2
MiniMax M2
$0.26
3
MiniMax M2.5
$0.27
4
MiniMax M3
$0.30
5
MiniMax M3 (batch)
$0.30
6
MiniMax M2.7
$0.30
7
MiniMax M2-her
$0.30
8
MiniMax M2.1
$0.30
9
MiniMax M1
$0.40

More from MiniMax

Other models by the same vendor in the catalogue.