Cydonia 24B V4.1 vs Mercury 2.5

Prices checked

Mercury 2.5 takes 4 of 5 rounds against Cydonia 24B V4.1. It is also the cheaper of the two to run, at $0.07 per million tokens against $0.35.

TheDrummer

Cydonia 24B V4.1

131k context · open weights

$0.35/M tokens

OpenRouter's own price · $0.21 per 1,000 pages

InceptionWins 4 rounds

Mercury 2.5

260k context · tool calling

$0.07/M tokens

Cheapest price, at Nous Portal · 3.3¢ per 1,000 pages

Maker's price in (lower wins)

$0.30/M

$0.20/M

Maker's price out (lower wins)

$0.50/M

$0.75/M

Cheapest price (lower wins)

none below the maker

$0.07/M at Nous Portal

Maker's price, blended (lower wins)

$0.35/M

$0.34/M

Cost per 1,000 pages (lower wins)

$0.21

3.3¢

Context

131k tokens

260k tokens

Open weights

yes

no

Tool calling

no

yes

Structured output

yes

yes

Reads images

no

no

Reasoning

no

yes

Released

27 Sept 2025

8 Sept 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

not published

Providers selling both · 2

  • Kilo Gateway$0.35 / $0.34
  • AI/ML API$0.37 / $0.36

Cydonia 24B V4.1, then Mercury 2.5, per million tokens.

Go further

Add a third or fourth model, or change the weighting, in the tool.

What moved this week

  1. Cydonia 24B V4.1

    NanoGPT · 13% cheaper ·

    $0.30 / $0.15 $0.35 / $0.16

Frequently asked

Which is cheaper, Cydonia 24B V4.1 or Mercury 2.5?
Mercury 2.5, at $0.07 per million tokens against $0.35 for Cydonia 24B V4.1, blended 3 in : 1 out, read on 31 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 2.5: $0.07 at Nous Portal.
Can I buy both from one provider?
Yes. 2 providers sell both: Kilo Gateway, AI/ML API. The cheapest of them for the two together is Kilo Gateway.
Which holds more context?
Mercury 2.5, at 260k tokens against 131k.

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

More