MiniMax › MiniMax M3 › Pricing

MiniMax M3 pricing

API list price by MiniMax · checked Oct 23, 2026
Benchmarks and alternatives →
$0.30 / $1.20per 1M tokens in / out
$0.06cache read · −80%
$0.51per task at thinking?
#24on OpenRouter by tokens · 1.4T / week

Price sheetper 1M tokens

Input$0.30list
Output$1.20
Cache read$0.06−80% vs input
Context · max output524K · 512Ktokens

Where to buy12 providers · per 1M tokens

ProviderInputOutputContext
CoreWeave$0.23$0.96262K
DeepInfra$0.28$1.10—
fireworks$0.30$1.20—
Minimaxlab$0.30$1.20524K
ModelRun$0.30$1.301M
Novita$0.30$1.201M
Parasail$0.30$1.201M
Together$0.30$1.20524K
Venice$0.30$1.20524K
Featherless$0.55$2.20—
Mara$0.60$2.401M
SambaNova$0.60$2.401M

In MiniMax's line-upper 1M in / out

MiniMax M3.1 Flash$0.15 / $0.60−50%
MiniMax 01$0.20 / $1.10−19%
MiniMax M2-her$0.30 / $1.200%
MiniMax M3$0.30 / $1.20this model
MiniMax M1$0.40 / $2.20+62%
MiniMax M2.7-highspeed$0.60 / $2.402×
MiniMax M2.5 Highspeed$0.60 / $2.402×
<
All MiniMax API prices →

Cheaper for the same workvs MiniMax M3

GPT-6.1 Sol xhigh-23%score +75%$0.39
MiMo v2.6 Pro thinkingOpen-74%score +59%$0.13
DeepSeek V4.1 Flash 1017 maxOpen-48%score +54%$0.26
Claude Haiku 5.5 max-58%score +49%$0.21
MiniMax M3.1 Flash thinking-57%score +46%$0.22
All alternatives and what breaks when you switch →

Pricing questions

How much does MiniMax M3 cost?›

$0.30 per 1M input tokens and $1.20 per 1M output tokens. Cached input is $0.06. One Intelligence Index task costs about $0.51 at the default effort.

Is MiniMax M3 free to use?›

There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.

How much does prompt caching save?›

Cache reads cost $0.06 per 1M, 80% below the input price.

Is MiniMax M3 cheaper than MiniMax M2.7?›

It costs the same per token: $0.30 / $1.20.

What is a cheaper alternative to MiniMax M3?›

GPT-6.1 Sol at xhigh effort costs -23% per task with a score +75% on Humanity's Last Exam.