MiniMax-M2 vs MiniMax-M3
Prices checked
MiniMax-M3 takes 2 of 5 rounds against MiniMax-M2. It is also the cheaper of the two to run, at $0.38 per million tokens against $0.40.
MiniMaxMiniMax-M2
205k context · tool calling · open weights
$0.40/M tokensCheapest price, at LLM Gateway · $0.18 per 1,000 pages
MiniMaxWins 2 roundsMiniMax-M3
1M context · tool calling · reads images · open weights
$0.38/M tokensCheapest price, at Vultr Serverless Inference · $0.17 per 1,000 pages
Maker's price in (lower wins)
$0.30/M
$0.30/M
Maker's price out (lower wins)
$1.20/M
$1.20/M
Cheapest price (lower wins)
$0.40/M at LLM Gateway
$0.38/M at Vultr Serverless Inference
Maker's price, blended (lower wins)
$0.52/M
$0.52/M
Cost per 1,000 pages (lower wins)
$0.18
$0.17
Context
205k tokens
1M tokens
Open weights
yes
yes
Tool calling
yes
yes
Structured output
not published
no
Reads images
no
yes
Reasoning
yes
yes
Released
27 Oct 2025
1 Jun 2026
Providers selling it
21
69
Price we measure against
the maker's own
the maker's own
Trains on your prompts (no is better)
not published
not published
Providers selling both · 19
Nous Portal$0.45 / $0.41
LLM Gateway$0.40 / $0.48
NanoGPT$0.51 / $0.41
Kilo Gateway$0.45 / $0.53- MiniMax$0.45 / $0.53
OpenRouter$0.45 / $0.53
TrustedRouter$0.55 / $0.44
Eden AI$0.53 / $0.53
MiniMax-M2, then MiniMax-M3, per million tokens; the 8 cheapest of 19.
Go further
Add a third or fourth model, or change the weighting, in the tool.
What moved this week
Kenari · 900% dearer · $0.63 / $2.50 6.3¢ / $0.25- Kilo Gateway · 15% cheaper · $0.26 / $1.02 $0.30 / $1.20
- Kilo Gateway · 35% dearer · $0.30 / $1.20 $0.22 / $0.88
- Eden AI · 47% cheaper · $0.30 / $1.20 $0.49 / $2.47
Frequently asked
- Which is cheaper, MiniMax-M2 or MiniMax-M3?
- MiniMax-M3, at $0.38 per million tokens against $0.40 for MiniMax-M2, blended 3 in : 1 out, read on 31 Oct 2026.
- Where is each one cheapest?
- MiniMax-M2: $0.40 at LLM Gateway. MiniMax-M3: $0.38 at Vultr Serverless Inference.
- Can I buy both from one provider?
- Yes. 19 providers sell both: Nous Portal, LLM Gateway, NanoGPT, Kilo Gateway, MiniMax, OpenRouter, and more. The cheapest of them for the two together is Nous Portal.
- Which holds more context?
- MiniMax-M3, at 1M tokens against 205k.
Prices exclude tax, read 31 Oct 2026 from each provider's own catalog. They are per M tokens, blended 3 in : 1 out, and a page is 600 tokens in and 60 out. Bars are scaled to the larger value in each row.
Related comparisons