Model dossier

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,...

ProviderMiniMax Start comparison

Context1,048,576

Max output131,072

Pricing viewTVP price

Identity

MiniMax: MiniMax M3

Model ID: minimax/minimax-m3
Canonical slug: minimax/minimax-m3-20260531
Knowledge cutoff: n/a
Created: 5/31/2026

Capabilities

textimagevideotoolsstructured

Modalities

text+image+video->texttextimagevideo

Capacity

Context1,048,576

Max output131,072

TokenizerOther