TheDrummer Cydonia 24B: a fine-tune for long-form fiction
Thedrummer
Services found: 1
| # | AI model | Capabilities | API $/1M (in / out) | Context window | Price / mo | Output $/1M | Overview | Visit site |
|---|---|---|---|---|---|---|---|---|
| 1 |  Cydonia 24B V4.1 Thedrummer |    | $0.3 / $0.5 | 131.1K tokens | API only | 0.5 | View |
Browse by need
TheDrummer is a community maintainer rather than a lab: the entries here are fine-tunes of open-weight base models, published on Hugging Face and served by third-party hosts rather than a first-party API.
That changes what the numbers mean. There is no vendor price list, no support contract and no deprecation policy — you get weights and a community. For experimentation and self-hosting that is often enough; for production it is a different risk profile from a commercial vendor.
Community fine-tuneBuilt on open base models, not an original line.
No vendor contractNo support, SLA or deprecation policy.
Self-host or third partyServed by community hosts rather than a first-party API.
Models from this vendor
1 Thedrummer model in this rating. Prices are input and output per 1M tokens from the vendor official price list; for dirhams multiply by 3.6725. Tap a card to open the model page.
How to choose
- Benchmark against a comparable model from a larger vendor before committing production traffic — line-ups this size get less independent testing.
- Start with Cydonia 24B V4.1 at $0.3 / $0.5 per 1M tokens; it is the cheapest entry point here.
- Check the context window against your longest input — the largest here is Cydonia 24B V4.1 at 131.1K tokens.
- Confirm support terms and deprecation policy, which smaller vendors document less thoroughly.
Common mistakes
Assuming parity with the majorsOn the hardest tasks the frontier labs remain ahead; compare on your own cases.
Skipping the exit planA smaller vendor can change terms or availability faster. Identify a fallback model before you depend on this one.
Who this suits
Cost-driven teamsCydonia 24B V4.1 at $0.3 / $0.5 undercuts most mainstream options.
EvaluatorsA useful comparison point when benchmarking the single model against larger line-ups.
Regional usersRelevant where this vendor platform or language coverage matters more than raw capability.
Related filters
Text & chat228 models for text generation and chat
MultilingualAll 239 models work beyond English
Proprietary API151 closed-weight, API-only models
Alibaba (Qwen)34 models in this rating
OpenAI30 models in this rating
Google DeepMind17 models in this rating
Frequently asked questions
Is this a company?
No — a community maintainer publishing fine-tunes of open-weight models.
Where do I run it?
Self-hosted, or through third-party providers that host community models.
Should I use it in production?
Only with the understanding that there is no vendor behind it.
How many Thedrummer models are in this rating?
1, covering text & chat, multilingual, proprietary API.
Is Thedrummer a good default choice?
For most teams no — start with a mainstream vendor and use this one where its pricing or specialisation gives a concrete advantage.
Frequently searched
By capabilityReasoningCodingVisionLong context 1M+Free tierOpen weightsLow latencyRealtime voiceImage generation
By vendorAnthropic (13)OpenAI (30)Google DeepMind (17)xAI (8)Meta (6)DeepSeek (9)Mistral AI (11)Alibaba (Qwen) (34)Z.ai (12)Moonshot AI (5)
Rate this page
Help us improve