MiniMax-M2 vs MiniMax-M2.1.
model vs model · prices as of
MiniMax-M2 takes 1 of 5 rounds against MiniMax-M2.1. It is also the cheaper of the two to run, at $1.60 per million tokens against $1.91.
MiniMax-M2
$1.60/M tokens
cheapest we can explain, at LLM Gateway · $0.18 per 1,000 pages
205k context · tool calling · open weights
MiniMax-M2.1
$1.91/M tokens
cheapest we can explain, at LLM Gateway · $0.228 per 1,000 pages
205k context · tool calling · open weights
List price in (lower wins)
$0.30/M
$0.30/M
List price out (lower wins)
$1.20/M
$1.20/M
Cheapest we can explain (lower wins)
$1.60/M at LLM Gateway
$1.91/M at LLM Gateway
Standard price (lower wins)
$2.10/M
$2.10/M
Cost per 1,000 pages (lower wins)
$0.18
$0.228
Context
205k tokens
205k tokens
Open weights
yes
yes
Tool calling
yes
yes
Structured output
not stated
not stated
Reads images
no
no
Reasoning
yes
yes
Released
27 Oct 2025
23 Dec 2025
Providers selling it
22
24
Price we measure against
the maker's own
the maker's own
Trains on your prompts (no is better)
not stated
not stated
Providers selling both · 18
LLM Gateway$1.60 / $1.91
MiniMax$1.79 / $2.10
Nous Portal$1.79 / $2.10
OpenRouter$1.79 / $2.10
Eden AI$2.10 / $2.10
Hugging Face Inference Providers$2.10 / $2.10
Kilo Gateway$2.10 / $2.10
Merge Gateway$2.10 / $2.10
MiniMax-M2 then MiniMax-M2.1, per million tokens · showing the 8 cheapest of 18
Go further
Add a third or fourth model, or switch the weighting, in the tool.
What moved in the last seven days
- MiniMax-M2
Nous Portal$0.20 / $0.82 $0.26 / $1.0225% dearer · - MiniMax-M2.1
Nous Portal$0.24 / $0.96 $0.30 / $1.2025% dearer ·
Frequently asked
- Which is cheaper, MiniMax-M2 or MiniMax-M2.1?
- MiniMax-M2, at $1.60 per million tokens against $1.91 for MiniMax-M2.1, three parts input to one part output, read on 16 Sept 2026.
- Where is each one cheapest?
- MiniMax-M2: $1.60 at LLM Gateway. MiniMax-M2.1: $1.91 at LLM Gateway.
- Can I buy both from one provider?
- Yes. 18 providers sell both: LLM Gateway, MiniMax, Nous Portal, OpenRouter, Eden AI, Hugging Face Inference Providers, and more. The cheapest of them for the two together is LLM Gateway.
- Which holds more context?
- Both hold 205k tokens in one call.
Prices exclude tax and are per million tokens, read 16 Sept 2026 from each provider's own catalog. The standard price blends three parts input to one part output; a page is 600 tokens in and 60 out. Bars are scaled to the larger value in each row.