Models / Uncensored / soob3123
Veiled Calla 12B API pricing
$1.05 in, $1.05 out per million tokens.
Price · per million tokens, USD
Get a key| Tokens | soob3123 list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $1.05 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $1.05 | — |
Veiled Calla 12B specs
- Context window
- 32,768 tokens
- Max output
- 8,192 tokens
- Input
- text
Veiled Calla 12B: soob3123’s atmospheric roleplay tune of Gemma 3 · mystery and slow-burn scenes on a 12B base
Veiled Calla 12B is soob3123's roleplay tune of Google's Gemma 3 12B, trained on the author's own roleplay dataset (its card, created 2025-04-16). The card pitches it at immersive, atmospheric scenes: mysteries that unfold, characters that stay consistent over long sessions, and the unspoken feeling between them. It says the model is uncensored in roleplay mode, with a system prompt as SillyTavern sends one, and still refuses in assistant mode without one. It is served as veiled-calla-12b at $1.05 input and $1.05 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.
| Veiled Calla 12B | |
|---|---|
| Base model | Gemma 3 12B |
| Made by | soob3123 |
| Method | Fine-tune on soob3123’s roleplay dataset |
| License on the card | apache-2.0 |
| Context window here | 32,768 tokens |
| Downloads, 30 days to 2026-10-21 | 38 |
| Card | soob3123/Veiled-Calla-12B |
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":"veiled-calla-12b","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'Veiled Calla 12B 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 Veiled Calla 12B: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $1.05 input and $1.05 output per million tokens, that is $2.10 + $0.525 = $2.63, paid from prepaid credit with no subscription.
Veiled Calla 12B 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="veiled-calla-12b",
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: 'veiled-calla-12b',
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":"veiled-calla-12b","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 soob3123
Veiled Calla 12B questions
- What is Veiled Calla 12B?
- Veiled Calla 12B is a model from soob3123, with a 32,768-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as veiled-calla-12b.
- How much does the Veiled Calla 12B API cost?
- $1.05 per million input tokens and $1.05 per million output tokens.
- Is Veiled Calla 12B 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 $0.0016.
- What is the Veiled Calla 12B context window?
- Veiled Calla 12B has a 32,768-token context window, with up to 8,192 output tokens per request. It takes text input.
- What is the Veiled Calla 12B model id?
- veiled-calla-12b. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a Veiled Calla 12B 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 Veiled Calla 12B and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
- Is there a Veiled Calla 12B API?
- Yes: veiled-calla-12b on the OpenAI format at https://api.uplinkswitch.com/v1, $1.05 input and $1.05 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 Veiled Calla 12B based on?
- Google’s Gemma 3 12B instruction-tuned model, fine-tuned by soob3123 on the soob3123/rp_dataset roleplay set, per the Veiled Calla card.
- What license does Veiled Calla 12B have?
- The card lists Apache-2.0. Its base, Gemma 3 12B, is under Google’s Gemma terms of use.
- What does Veiled Calla 12B cost per 100 messages?
- $0.2625 for 100 chat turns of 2,000 input and 500 output tokens each, at $1.05 input and $1.05 output per million tokens, from prepaid credit with no subscription.
- Is Veiled Calla 12B uncensored?
- In roleplay, per its card: with a character and a system prompt, as SillyTavern sends them, it does not refuse. Without a system prompt, in plain assistant mode, the card says it still refuses, and points to soob3123’s Amoral models for a fully uncensored assistant.
- What is Veiled Calla 12B good at?
- Its card lists atmospheric depth, character consistency over long sessions, narrative mystery and emotional nuance, and says it may answer too cryptically in some contexts.