Model registry / MiniMax / Minimax / MiniMax-M2
MiniMax-M2
Efficient open MiniMax model built for coding agents and tool-heavy workflows
Line
Minimax
Weights
Open
Released
2025-10-27
Context
205K
Input
$0.17 / 1M
Output
$1.00 / 1M
Max output
131K
Coverage
not covered yet
Overview
MiniMax-M2 is an open model from MiniMax, built for coding agents and tool-heavy workflows. It is the first version of its line in the registry. It has a context window of 204800 tokens and a maximum output of 131072 tokens. It accepts and returns text. It supports reasoning mode and tool calling. Weights are open. Price starts at $0.17 per million input tokens and $1.00 per million output tokens, with cached input at $0.03 per million tokens.
Specs
Pricing
First version of its line in the registry.
Range across the hosts that serve it: up to $0.349 per 1M input tokens.
Strengths
- 204800 token context window
- 131072 token max output
- Reasoning mode for complex tasks
- Tool calling for agent workflows
- Open weights for self-hosting
Best for
- Reach for it for coding agent development
- Reach for it for tool-heavy automation
- Reach for it for long-context reasoning tasks
How to access
19 hosts serve this model at the price above · the maker's documentation
Minimax: every version
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 and output limit?
- Context window is 204800 tokens, max output is 131072 tokens.
- Does it support reasoning and tool calling?
- Yes, it supports reasoning mode and tool calling.
- Is the model open weights?
- Yes, weights are open.