Models / Uncensored / PocketDoc
DansPE 1.3 24B API pricing
$2.908 in, $11.632 out per million tokens.
Price · per million tokens, USD
Get a key| Tokens | PocketDoc list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $2.908 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $11.632 | — |
DansPE 1.3 24B specs
- Context window
- 32,768 tokens
- Input
- text
DansPE 1.3 24B: PocketDoc’s PersonalityEngine on Mistral Small · roleplay, co-writing and technical work in ten languages
DansPE 1.3 24B is PocketDoc's Dans-PersonalityEngine V1.3.0, a fine-tune of Mistral AI's Mistral Small 3.1 24B Base (its card, created 2025-05-08). The card describes a series trained on more than 50 datasets to do both creative work, roleplay and co-writing, and technical work, code, tool use and reasoning. V1.3.0 adds ten languages, with English still the strongest. It was trained with Axolotl on eight H100s for 50 hours, with compute from Prime Intellect and Kalomaze. The card gives 32,768 tokens of context, 131,072 with degraded recall, and its own chat format, DanChat-2, with a special token per role. It is served as dans-pe-1.3-24b at $2.908 input and $11.632 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.
| DansPE 1.3 24B | |
|---|---|
| Base model | Mistral Small 3.1 24B Base |
| Made by | PocketDoc |
| Method | Fine-tune with Axolotl on 50+ datasets, 8 H100s for 50 hours |
| License on the card | apache-2.0 |
| Context window here | 32,768 tokens |
| Downloads, 30 days to 2026-10-21 | 457 |
| Card | PocketDoc/Dans-PersonalityEngine-V1.3.0-24b |
From the Hugging Face card and its API record, read 2026-10-21.
The card recommends temperature 1.0 and top_p 0.9, and publishes a SillyTavern master template for its DanChat-2 format.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"dans-pe-1.3-24b","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'DansPE 1.3 24B 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 DansPE 1.3 24B: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $2.908 input and $11.632 output per million tokens, that is $5.816 + $5.816 = $11.63, paid from prepaid credit with no subscription.
DansPE 1.3 24B 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="dans-pe-1.3-24b",
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: 'dans-pe-1.3-24b',
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":"dans-pe-1.3-24b","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.
DansPE 1.3 24B questions
- What is DansPE 1.3 24B?
- DansPE 1.3 24B is a model from PocketDoc, with a 32,768-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as dans-pe-1.3-24b.
- How much does the DansPE 1.3 24B API cost?
- $2.908 per million input tokens and $11.632 per million output tokens.
- Is DansPE 1.3 24B 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 $0.0087.
- What is the DansPE 1.3 24B context window?
- DansPE 1.3 24B has a 32,768-token context window. It takes text input.
- What is the DansPE 1.3 24B model id?
- dans-pe-1.3-24b. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a DansPE 1.3 24B 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 DansPE 1.3 24B and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
- Is it the real DansPE 1.3 24B?
- Every day each model gets the same test prompt, and a model always counts that prompt the same way; a swapped one would not. DansPE 1.3 24B's latest result: Same fingerprint since Oct 21.
- Is there a DansPE 1.3 24B API?
- Yes: dans-pe-1.3-24b on the OpenAI format at https://api.uplinkswitch.com/v1, $2.908 input and $11.632 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 DansPE 1.3 24B based on?
- Mistral AI’s Mistral Small 3.1 24B base model (not the instruct), fine-tuned by PocketDoc on more than 50 roleplay, writing, assistant, tool-use and reasoning datasets, per the Dans-PersonalityEngine V1.3.0 card.
- What license does DansPE 1.3 24B have?
- The card lists Apache-2.0, the license of its Mistral Small 3.1 base.
- What does DansPE 1.3 24B cost per 100 messages?
- $1.1632 for 100 chat turns of 2,000 input and 500 output tokens each, at $2.908 input and $11.632 output per million tokens, from prepaid credit with no subscription.
- Which languages does DansPE 1.3 24B support?
- Ten, per its card: Arabic, Chinese, English, French, German, Hindi, Japanese, Korean, Portuguese and Spanish. English remains the primary language and where the card expects peak performance.
- Is DansPE 1.3 24B only for roleplay?
- No. The card lists roleplay and storywriting alongside code, tool use, chemistry, biology, legal, medical and finance tags, and its datasets cover assistant, task, tool and reasoning data as well as prose.
- DansPE 1.3 24B or Cydonia 24B v4.3?
- Both are 24B Mistral Small tunes: DansPE is a general-purpose and roleplay tune of the 3.1 base model; Cydonia v4.3 is a roleplay tune of Mistral Small 3.2 Instruct. DansPE 1.3 24B is $2.908 / $11.632 per million tokens in / out, $11.63 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.