MiniMax: MiniMax M3

MINIMAX Developer Architecture Profile

OpenRouter ↗HuggingFace ↗

Intelligence (ELO)1415Chatbot Arena Verified

Max Context Limit1,048,576Max Out: 512,000 tokens

Prompt Caching80% OFF$0.06 / 1M cached

Standard API / 1M$1.50Blended Standard Rate

Model Capabilities & Contract SLAs

Drafting
Classification
Coding & Logic
Fictional

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,...

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.30 / 1M

⚡ Cached Input (Prompt Cache Read)80% OFF$0.06 / 1M

Output Tokens (Completion)$1.20 / 1M

Pricing data via OpenRouter. Sync: 10/2/2026

Evaluate Competitors

VS Engine MatchupMiniMax: MiniMax M3 vs SpaceXAI: Grok Build 0.1 VS Engine MatchupMiniMax: MiniMax M3 vs Perceptron: Perceptron Mk1 VS Engine MatchupMiniMax: MiniMax M3 vs Inception: Mercury 2 VS Engine MatchupMiniMax: MiniMax M3 vs Qwen: Qwen-Plus VS Engine MatchupMiniMax: MiniMax M3 vs Perceptron: Perceptron Mk1.5 VS Engine MatchupMiniMax: MiniMax M3 vs Sakana: Sakana Namazu