Models / Uncensored / TheDrummer
Magidonia 24B v4.3 API pricing
$0.3535 in, $0.4235 out per million tokens.
Price · per million tokens, USD
Get a key| Tokens | TheDrummer list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $0.3535 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $0.4235 | — |
Magidonia 24B v4.3 specs
- Context window
- 32,768 tokens
- Input
- text
Magidonia 24B v4.3: TheDrummer’s Magistral Small roleplay tune · the Magistral counterpart of Cydonia v4.3, per token
Magidonia 24B v4.3 is TheDrummer's roleplay and story-writing tune of Mistral AI's Magistral Small 2509 (its card, created 2025-11-29). The card names Mistral v7 Tekken as its chat template, says thinking in <thinking> tags works and so does no thinking, and points to Cydonia 24B v4.3 as its Mistral Small 3.2 counterpart: the difference is mostly writing style, and most of its testers prefer the Magistral tune. Its What's New is two lines, much better roleplay, and a note that it can lean more positive. It is served as magidonia-24b-v4.3 at $0.3535 input and $0.4235 output per million tokens, one of 146 builds in the uncensored LLM API, on the same key as every other model. Added 2026-10-21.
| Magidonia 24B v4.3 | |
|---|---|
| Base model | Magistral Small 2509 |
| Made by | TheDrummer |
| Method | Fine-tune for roleplay and story writing |
| License on the card | none listed (base: Apache-2.0) |
| Context window here | 32,768 tokens |
| Downloads, 30 days to 2026-10-21 | 901 |
| Card | TheDrummer/Magidonia-24B-v4.3 |
From the Hugging Face card and its API record, read 2026-10-21.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"magidonia-24b-v4.3","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'Magidonia 24B v4.3 next to the other uncensored models · per million tokens, live
A chat turn is 2,000 input and 500 output tokens. Live from the catalog, ordered by the cost of 1,000 turns.
Worked for Magidonia 24B v4.3: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $0.3535 input and $0.4235 output per million tokens, that is $0.707 + $0.2118 = $0.92, paid from prepaid credit with no subscription.
Magidonia 24B v4.3 API · base URL and key
from openai import OpenAI
client = OpenAI(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
completion = client.chat.completions.create(
model="magidonia-24b-v4.3",
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.uplinkswitch.com/v1',
apiKey: 'sk-uplink-live-...',
});
const completion = await client.chat.completions.create({
model: 'magidonia-24b-v4.3',
messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"magidonia-24b-v4.3","messages":[{"role":"user","content":"Hello"}]}'What would it cost? · paste a prompt, priced before you send it
Input is counted at about 4 characters per token.
Cheapest first. A real request is billed on the provider's own token count. Same estimate as JSON: POST https://api.uplinkswitch.com/v1/estimate, no key needed.
More from TheDrummer
Magidonia 24B v4.3 questions
- What is Magidonia 24B v4.3?
- Magidonia 24B v4.3 is a model from TheDrummer, with a 32,768-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as magidonia-24b-v4.3.
- How much does the Magidonia 24B v4.3 API cost?
- $0.3535 per million input tokens and $0.4235 per million output tokens.
- Is Magidonia 24B v4.3 free?
- It is pay as you go: prepaid credit from $10, with no subscription or monthly fee, billed per token. A 1,000-token prompt with a 500-token reply costs about $0.0006.
- What is the Magidonia 24B v4.3 context window?
- Magidonia 24B v4.3 has a 32,768-token context window. It takes text input.
- What is the Magidonia 24B v4.3 model id?
- magidonia-24b-v4.3. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a Magidonia 24B v4.3 API key?
- Create one in the console at uplinkswitch.ai/console: prepaid credit from $10, no subscription, and the key is live at once. The same key calls Magidonia 24B v4.3 and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
- Is there a Magidonia 24B v4.3 API?
- Yes: magidonia-24b-v4.3 on the OpenAI format at https://api.uplinkswitch.com/v1, $0.3535 input and $0.4235 output per million tokens. No weights to download and no GPU of your own; the key also runs every other model in the catalog.
- What is Magidonia 24B v4.3 based on?
- Mistral AI’s Magistral Small 2509, the 24B reasoning model, fine-tuned by TheDrummer for roleplay and story writing, per the Magidonia 24B v4.3 card.
- What license does Magidonia 24B v4.3 have?
- The Magidonia card lists no license. Its base, Magistral Small 2509, is Apache-2.0.
- What does Magidonia 24B v4.3 cost per 100 messages?
- $0.0919 for 100 chat turns of 2,000 input and 500 output tokens each, at $0.3535 input and $0.4235 output per million tokens, from prepaid credit with no subscription.
- Does Magidonia 24B v4.3 think before it answers?
- It can. Its card says thinking in <thinking> tags works, [THINK] tags might, and no thinking works too, so the choice is yours per request. Thinking tokens bill as output.
- Magidonia 24B v4.3 or Cydonia 24B v4.3?
- Same tune, two bases: Magidonia is on Magistral Small 2509, Cydonia v4.3 on Mistral Small 3.2. The Magidonia card says the difference is mostly writing style and that most people prefer the Magistral tune. Magidonia 24B v4.3 is $0.3535 / $0.4235 per million tokens in / out, $0.92 for 1,000 chat turns; Cydonia 24B v4.3 is $0.484 / $0.60 per million tokens in / out, $1.27 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.