minimaxListed Dec 23, 2025

MiniMax: MiniMax M2.1

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...

Context window204.8K
Max output131.1K
Provider endpoints3
Benchmark results0
Measured performance

Benchmark results

All leaderboards ↗
—

No published results in this index yet

Scores appear here when an evaluation matches this exact model.

Access & cost

Prices across providers

3 quotes

Your token mix

USD · listed token rates

Minimax · via OpenRouterminimax/fp8 · quantization=fp8
$0.60
Minimax · via OpenRouterminimax/highspeed · tier=priority · quantization=fp8
$0.90

OpenRouter

Catalog quote
Input
$0.30
Output
$1.20
Cached input
$0.03
USD / 1M tokens
204.8K context131.1K max outputPrice source ↗Checked Oct 18, 2026
Endpoint IDminimax/minimax-m2.1

Minimax

via OpenRouter

minimax/fp8 · quantization=fp8

Input
$0.30
Output
$1.20
Cached input
$0.03
USD / 1M tokens
204.8K context131.1K max outputPrice source ↗Checked Oct 18, 2026
Endpoint IDminimax/minimax-m2.1::minimax/fp8

Minimax

via OpenRouter

minimax/highspeed · tier=priority · quantization=fp8

Input
$0.30
Output
$2.40
Cached input
$0.03
USD / 1M tokens
204.8K context131.1K max outputPrice source ↗Checked Oct 18, 2026
Endpoint IDminimax/minimax-m2.1::minimax/highspeed

Model specifications

Developer
minimax
Modality
Language
Context
204,800 tokens
Maximum output
131,072 tokens
Weights
Open weights
Provider listed
Dec 23, 2025
First discovered
Oct 16, 2026

Exact identities

  • openrouterminimax/minimax-m2.1

Sources

Updated Oct 18, 2026

More from minimax

View all ↗
minimaxListed Sep 3

H3 Max Director

Direct continuous, realtime video streams with live prompts while preserving characters, settings, and story continuity.

No reported score
No reported score
Price not listed