minimaxtext + image + video → text
MiniMax: MiniMax M3
Canonical ID: minimax/minimax-m3
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
VerifiedIntelligence 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)
Input$0.30
Completion Output (1M Tokens)
Output$1.20
Prompt KV-Cache Read (1M Tokens)
Cached$0.06
Context Window Capacity
Context1,024k tokens
Supported Parameters & Features
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p