Compute Screener
Updated 1:08 AM CDT

MiniMax M3 API price per 1M tokens: input, cached and output prices, price chart and history

# Lab/Bloomberg ticker USD / 1M tokens 1D 1W 1M Trend Chart (3M)
1
Alibaba
$0.0675-2.7%+20.5%+16.8%▼ Strong 7.2-52.3% a month
2
AnthropicORNNTOKA
$0.545+1.3%-15.8%-35.8%▼ Strong 5.8-22.0% a month
3
DeepSeek
$0.0279+0.4%-2.8%-4.8%▼ Strong 5.4-34.2% a month
4
StepFun
$0.220-1.1%-5.9%+213.1%▲ Strong 4.5+63.5% a month
5
Z.ai
$0.133+4.0%-8.9%-21.6%▼ Moderate 3.3-31.7% a month
6
Google
$0.232-10.8%+4.9%+66.4%▲ Moderate 3.1+16.8% a month
7
Meta
$0.01570.0%0.0%0.0%▼ Moderate 3.0-62.0% a month
8
MiniMax
$0.0422+14.1%-35.2%-57.9%▼ Moderate 2.5-16.0% a month
9
Xiaomi
$0.0333-6.7%+1.2%+28.1%▲ Moderate 2.5+15.9% a month
10
Moonshot AI
$0.629+6.3%+2.3%-18.4%▼ Weak 1.7-4.1% a month
11
xAI
$0.7350.0%0.0%0.0%▲ Weak 1.7+3.9% a month
12
OpenAIORNNTOKO
$0.157-9.2%-14.4%-74.6%▼ Weak 0.8-10.6% a month
13
NVIDIA
$0.2000.0%0.0%0.0%Weak 0.00.0% a month

MiniMax M3MiniMax

$0.1000.0% (All)
USD / 1M tokens
Cache read $0.06 · Input $0.30 · Output $1.20 per 1M tokens, at 87% cache read, 12% input, 1% output
1D
1W
1M
3M
6M
YTD
1Y
0.0%
0.0%
0.0%
0.0%
—
—
—
#ModelAs ofShareUSD / 1M tokens
1MiniMax M3.1 FlashNov 1, 1:09 AM CDT91.8%$0.0370
2MiniMax M3Nov 1, 1:09 AM CDT8.2%$0.100

Break-even throughput by GPU

GPUUSD / GPU-hourTokens/s per GPU
B300$8.894,706
B200$7.784,116
H200$5.092,695
H100$3.691,952
RTX PRO 6000$2.061,087
A100$1.75928
L40S$1.41746
L40$0.95503
RTX 6000 Ada$0.91480
RTX A6000$0.57303
RTX 4090$0.53282

Gross margin calculator

Revenue—
GPU rental price$3.69
Gross profit—
Gross margin—

About MiniMax M3

MiniMax M3 is a model from MiniMax. Its posted API price is $0.30 per 1M input tokens, $0.06 per 1M cached input tokens and $1.20 per 1M output tokens, or $0.100 per 1M tokens at the mix of tokens agents send (87% cache read, 12% input, 1% output). Its price has not changed since Jun 1, 2026. It carries 8.2% of MiniMax's API tokens and is one of the 2 models in the MiniMax token price index, $0.0422 per 1M tokens today. Of the 36 models in the token index it is the 22nd most expensive. At today's H100 rental price of $3.69 per GPU-hour, its break-even throughput is 1,952 tokens per second per GPU at its list price (3 input : 1 output). Prices are collected once a day, for each UTC day.

Models near this price

  • Gemini 3 Flash Preview (Google): $0.134 per 1M tokens at the mix, $0.50 input and $3.00 output
  • DeepSeek V4 Pro 0813 (DeepSeek): $0.118 per 1M tokens at the mix, $0.66 input and $1.98 output
  • Step 3.7 Flash (StepFun): $0.0703 per 1M tokens at the mix, $0.20 input and $1.15 output
  • Gemini 3.1 Flash Lite (Google): $0.0668 per 1M tokens at the mix, $0.25 input and $1.50 output
  • MiMo-V2.6-Pro (Xiaomi): $0.0640 per 1M tokens at the mix, $0.435 input and $0.87 output
  • GPT-5.6 Luna (OpenAI): $0.0534 per 1M tokens at the mix, $0.20 input and $1.20 output

Cite as: Compute Screener, “MiniMax M3 API price”, computescreener.com/models/minimax-m3. The figures are free to reuse under CC BY 4.0 with credit to Compute Screener.