Models·TheDrummer

Cydonia 24B V4.1: What to know

thedrummer/cydonia-24b-v4.1

An open-weight, text-only model from TheDrummer for creative writing and other text tasks.

$0.30Input, per million tokens
$0.50Output, per million tokens
131KContext window
118KLongest answer

131K tokens of context — about 98,304 words, on a scale that ends at 2M.

What it can do

  • Open weights
  • Takes text
  • Gives text

Released 27 Sept 2025 · checked 3 Oct 2026.

About it

Cydonia 24B V4.1 is an open-weight text model from TheDrummer, based on Mistral Small 3.2 24B. Its stated strengths include creative writing, recall, following prompts, and reasoning. It can take up to 131,072 tokens at once and produce up to 117,964 tokens in one answer. Token prices are $0.3 per million input tokens and $0.5 per million output tokens.

Review

In a line

Cydonia 24B V4.1 is an open-weight model from TheDrummer that reads and writes text. It is based on Mistral Small 3.2 24B.

What it's good at

The model is described as suited to creative writing, with good recall and prompt following. It is also described as intelligent.

Price in plain terms

Input costs $0.3 per million tokens, and output costs $0.5 per million tokens.

At those rates, reading a roughly 500-word page costs about 0.019 cents. A chat turn with about 1,000 input tokens and 500 output tokens costs about 0.055 cents; 1,000 such turns cost about $0.55.

Context and limits

It can take in up to 131,072 tokens at once and write up to 117,964 tokens in one answer. It handles text only.

Ways to use it

The model has open weights, and its model ID is thedrummer/cydonia-24b-v4.1. The facts do not specify apps, chat tools, or providers that offer it.

Verdict

Consider Cydonia 24B V4.1 if you want an open-weight text model for creative writing and value its stated recall and prompt-following strengths. Its listed token prices come with example costs, though actual use depends on how much text you send and receive. It is not a fit for image tasks. Since no supported apps or providers are specified, check that a service you plan to use offers this model before choosing it.

Verdict

Cydonia 24B V4.1 is worth considering for people seeking open weights and a model described as good at creative writing, recall, and following prompts. Its text-only scope and per-token pricing make it easier to assess if your work is text-based and your usage is measurable. Avoid choosing it for image input or output.

  • Open weights are available.
  • Described as suited to creative writing.
  • Good recall and prompt adherence are listed strengths.
  • Can take up to 131,072 tokens at once.
  • Example costs are about $0.55 for 1,000 chat turns.
  • No supported apps, chat tools, or providers are specified.
  • A single answer is capped at 117,964 tokens.
  • Pick it ifPeople seeking open weights for text-based tasks; Creative writing and prompt-led text work
  • Skip it ifYou need image input or output.; You need a confirmed list of supported apps or providers.

Pricing

Input is $0.3 per million tokens and output is $0.5 per million tokens. The stated examples are about 0.019 cents to read a 500-word page, 0.055 cents per chat turn, and $0.55 per 1,000 such turns.

Questions

What is Cydonia 24B V4.1?

It is an open-weight, text-only model from TheDrummer, based on Mistral Small 3.2 24B.

What is it meant to do well?

Its stated strengths include creative writing, recall, following prompts, and intelligence.

How much does it cost?

Input is $0.3 per million tokens and output is $0.5 per million tokens. About 1,000 example chat turns cost $0.55.

How much text can it handle?

It can take up to 131,072 tokens at once and write up to 117,964 tokens in one answer.

Can it work with images?

No image capability is listed. Its inputs and outputs are text.

On these boards

More from TheDrummer