Hub/Models/minimax/minimax-m3
minimaxtext + image + video → text

MiniMax: MiniMax M3

Canonical ID: minimax/minimax-m3

Compare ModelOpen on OpenRouter →

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

Artificial Analysis Benchmarks

Verified
Intelligence Index18.9 / 100
Engineering Index26.2 / 100
Strategy & Ops27.9 / 100
Finance & Accounting25.1 / 100
Legal Index23.5 / 100
Healthcare & Medical21.7 / 100

Token Pricing & Economics

Prompt Input (1M Tokens)
$0.30
Input
Completion Output (1M Tokens)
$1.20
Output
Prompt KV-Cache Read (1M Tokens)
$0.06
Cached
Context Window Capacity
1,024k tokens
Context

Supported Parameters & Features

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p