Models / Uncensored / TheDrummer
Rocinante 12B v1.1 API pricing
$1.428 in, $2.0825 out per million tokens.
Price · per million tokens, USD
Get a key| Tokens | TheDrummer list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $1.428 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $2.0825 | — |
Rocinante 12B v1.1 specs
- Context window
- 16,384 tokens
- Max output
- 8,192 tokens
- Input
- text
Rocinante 12B v1.1: TheDrummer’s Mistral Nemo storyteller · a versatile workhorse for any adventure
Rocinante 12B v1.1 is TheDrummer's 12B storytelling model on Mistral Nemo (its card, created 2024-08-15, with 1,925 Hugging Face downloads in the 30 days to 2026-10-20). Testers on the card report richer, more distinct prose, more creativity and adventure-filled storytelling. The card credits MarinaraSpaghetti for its DELLA merge, and lists ChatML for roleplay, Alpaca for story and instruct adventure, and Mistral as its templates. It is served as rocinante-12b-v1.1 at $1.428 input and $2.0825 output per million tokens, one of 146 builds in the uncensored LLM API, on the same key as every other model. Added 2026-10-20.
| Rocinante 12B v1.1 | |
|---|---|
| Base model | Mistral Nemo 12B |
| Made by | TheDrummer |
| Method | Tune with a DELLA merge |
| License on the card | other |
| Context window here | 16,384 tokens |
| Downloads, 30 days to 2026-10-20 | 1,925 |
| Card | TheDrummer/Rocinante-12B-v1.1 |
From the Hugging Face card and its API record, read 2026-10-20.
The card suggests DRY, with temperature 0.7 for a familiar ride or 1.2 for more creativity.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"rocinante-12b-v1.1","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'Rocinante 12B v1.1 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 Rocinante 12B v1.1: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $1.428 input and $2.0825 output per million tokens, that is $2.856 + $1.0413 = $3.90, paid from prepaid credit with no subscription.
Rocinante 12B v1.1 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="rocinante-12b-v1.1",
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: 'rocinante-12b-v1.1',
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":"rocinante-12b-v1.1","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
Rocinante 12B v1.1 questions
- What is Rocinante 12B v1.1?
- Rocinante 12B v1.1 is a model from TheDrummer, with a 16,384-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as rocinante-12b-v1.1.
- How much does the Rocinante 12B v1.1 API cost?
- $1.428 per million input tokens and $2.0825 per million output tokens.
- Is Rocinante 12B v1.1 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 $0.0025.
- What is the Rocinante 12B v1.1 context window?
- Rocinante 12B v1.1 has a 16,384-token context window, with up to 8,192 output tokens per request. It takes text input.
- What is the Rocinante 12B v1.1 model id?
- rocinante-12b-v1.1. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a Rocinante 12B v1.1 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 Rocinante 12B v1.1 and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
- Is there a Rocinante 12B v1.1 API?
- Yes: rocinante-12b-v1.1 on the OpenAI format at https://api.uplinkswitch.com/v1, $1.428 input and $2.0825 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 Rocinante 12B v1.1 based on?
- Mistral AI’s Mistral Nemo 12B (the card lists a Mistral template for NeMo). TheDrummer tuned it for storytelling, with a DELLA merge by MarinaraSpaghetti, per the Rocinante 12B v1.1 card.
- What license does Rocinante 12B v1.1 have?
- The card’s license tag is other, with no license named. Mistral Nemo 12B is Apache-2.0.
- What does Rocinante 12B v1.1 cost per 100 messages?
- $0.3897 for 100 chat turns of 2,000 input and 500 output tokens each, at $1.428 input and $2.0825 output per million tokens, from prepaid credit with no subscription.
- What settings does Rocinante 12B v1.1 use?
- Its card suggests the DRY sampler, with temperature 0.7 for a calm, familiar ride and 1.2 for more creativity.
- Rocinante 12B v1.1 or UnslopNemo 12B v4.1?
- Both are TheDrummer’s 12B Mistral Nemo tunes: Rocinante v1.1 for storytelling and adventure, UnslopNemo v4.1 for adventure writing and roleplay. Rocinante 12B v1.1 is $1.428 / $2.0825 per million tokens in / out, $3.90 for 1,000 chat turns; UnslopNemo 12B v4.1 is $1.972 / $1.972 per million tokens in / out, $4.93 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.