AiCostCompare

MiniMax M3 (batch)

by MiniMax · minimax/minimax-m3:batch · #142 cheapest of 452 paid models

Prices updated Nov 17, 2026, 5:30 PM UTC · refreshed nightly

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,...

Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol

Pricing

Input

$0.224

per 1M tokens

Output

$0.88

per 1M tokens

Blended (3:1)

$0.388

3 input : 1 output

Cache read

$0.045

per 1M cached tokens

Cache write

—

per 1M tokens

Cache & batch economics

Effective prices for MiniMax M3 (batch) with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.388$0.0237—
50%$0.321$0.0148−38%
90%$0.267$0.0076−68%

*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.

What a request costs

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.000376$0.376
Document summary8,0001,000$0.002672$2.67
Codebase question (RAG)30,0002,000$0.00848$8.48
Long-context analysis150,0005,000$0.038$38.00

Performance

Intelligence Index

18.9

AA composite quality

Coding Index

58.6

Math Index

—

Agentic Index

29.5

Output speed

—

median

Time to first token

—

median

Time to first answer

—

after reasoning tokens

Design Arena Elo

CategoryElo
Website1,249
Web apps1,190
Full-stack1,175
Mobile apps1,169
Android native1,155
UI components1,233
Data viz1,229
SVG1,146
3D1,190
Game dev1,200
Agentic game dev1,110
HTML slides1,078
Python→PPTX slides1,167
Code categories1,236
ASCII art1,139
blender3d1,083
codetovideo1,219
pdf1,252
spreadsheet1,169

Specs

Context window

524K

tokens

Max output

512K

tokens

Input modalities

text, image, video

Tokenizer

Other