← All models
M

MiniMax: MiniMax M2

minimax/minimax-m2

Tool useJSONReasoningStreaming

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,...

Pricing

Input

$0.255 / 1M

Output

$1.00 / 1M

Specs

Context

204,800 tokens

Input

text

Output

text

Released: 2025-10

Supported parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

Open weights · HuggingFace

123,286 downloads/mo
1,495 likes
other text-generation
View on HuggingFace →