Back to every model

MiniMax

MiniMax M3 API pricing and specs

MiniMax's MiniMax M3: price per million tokens, context window, limits and capabilities, re-read from OpenRouter's model feed every 6 hours.

Input

$0.30

Output

$1.20

Context

1M

MiniMax M3 costs $0.30 per million input tokens and $1.20 per million output tokens. Cached input is billed at $0.06 per million, 80% less than fresh input.

Specifications

LabMiniMax
Model idminimax/minimax-m3
Input price$0.30 per million tokens
Output price$1.20 per million tokens
Cached input price$0.06 per million tokens
Context window1,048,576 tokens (1M)
Maximum output512,000 tokens (512K)
Tool callingyes
Image inputyes
Reasoningno
Intelligence index18.7
First listed31 May 2026

MiniMax's other models

ModelInput / 1MOutput / 1MContextListed
MiniMax M3.1 Flash$0.15$0.601M19 October 2026
MiniMax M2.7$0.30$1.20200K18 March 2026
MiniMax M2.5$0.30$1.20200K12 February 2026
MiniMax M2-her$0.30$1.2064K23 January 2026
MiniMax M2.1$0.30$1.20200K23 December 2025
MiniMax M2$0.255$1.02200K23 October 2025
MiniMax M1$0.55$2.201M17 June 2025
MiniMax-01$0.20$1.101M15 January 2025

Where these numbers come from

Read from OpenRouter's listing of MiniMax M3 every 6 hours into the catalog Founden's builders choose their models from. Prices are OpenRouter's listed price per million tokens: for a lab's closed models that is the lab's own list price, and for an open-weight model it is the price of the host OpenRouter routes to by default, which can differ from the lab's own API and from other hosts. US dollars, before batch, volume or regional discounts. Every model.