Cydonia 24B V4.1 vs Mercury 2
Prices checked
Cydonia 24B V4.1 takes 3 of 5 rounds against Mercury 2. It is also the cheaper of the two to run, at $0.35 per million tokens against $0.38.
Cydonia 24B V4.1
131k context · open weights
$0.35/M tokensOpenRouter's own price · $0.21 per 1,000 pages
InceptionMercury 2
128k context · tool calling
$0.38/M tokensInception's own price · $0.20 per 1,000 pages
Maker's price in (lower wins)
$0.30/M
$0.25/M
Maker's price out (lower wins)
$0.50/M
$0.75/M
Cheapest price (lower wins)
none below the maker
none below the maker
Maker's price, blended (lower wins)
$0.35/M
$0.38/M
Cost per 1,000 pages (lower wins)
$0.21
$0.20
Context
131k tokens
128k tokens
Open weights
yes
no
Tool calling
no
yes
Structured output
yes
yes
Reads images
no
no
Reasoning
no
yes
Released
27 Sept 2025
24 Feb 2026
Providers selling it
8
10
Price we measure against
OpenRouter
the maker's own
Trains on your prompts (no is better)
no provider to check
no provider to check
Providers selling both · 5
NanoGPT$0.30 / $0.38
Kilo Gateway$0.35 / $0.38
OpenRouter$0.35 / $0.38
TrustedRouter$0.37 / $0.40- AI/ML API$0.48 / $0.52
Cydonia 24B V4.1, then Mercury 2, per million tokens.
Go further
Add a third or fourth model, or change the weighting, in the tool.
Frequently asked
- Which is cheaper, Cydonia 24B V4.1 or Mercury 2?
- Cydonia 24B V4.1, at $0.35 per million tokens against $0.38 for Mercury 2, blended 3 in : 1 out, read on 21 Oct 2026.
- Where is each one cheapest?
- Cydonia 24B V4.1: nobody sells it below OpenRouter's own price with a stated reason, so $0.35 is the number to beat. Mercury 2: nobody sells it below the maker's own price with a stated reason, so $0.38 is the number to beat.
- Can I buy both from one provider?
- Yes. 5 providers sell both: NanoGPT, Kilo Gateway, OpenRouter, TrustedRouter, AI/ML API. The cheapest of them for the two together is NanoGPT.
- Which holds more context?
- Cydonia 24B V4.1, at 131k tokens against 128k.
Prices exclude tax, read 21 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