/ Models

Language models

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,...

Maker
Minimax
Context window
205K
Max output
131K
Input / 1M
$0.255
Output / 1M
$1.02
1M in + 1M out
$1.27

Everything else

Max output131K
Input / 1M$0.255
Output / 1M$1.02
Cache read / 1M
Cache write / 1M
1M in + 1M out$1.27
Takestext
Returnstext
Toolsyes
Reasoningalways on
Open weightsyes
Released2025-10-23
Knowledge cutoff
Retires
Catalog idminimax/minimax-m2

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models