Skip to content
OpenKey

Rocinante 12B

TheDrummerReleased Sep 30, 2024

Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity for vivid narratives -...

Try in playground
Context window
33K tokens
Input
text
Output
text
Tokenizer
Qwen
Knowledge cutoff
Apr 30, 2024
Released
Sep 30, 2024

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$0.250$0.0075$0.258
Output$0.500$0.015$0.515

Supported parameters

  • frequency_penalty
  • logit_bias
  • max_tokens
  • min_p
  • presence_penalty
  • repetition_penalty
  • seed
  • stop
  • temperature
  • top_k
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model thedrummer/rocinante-12b.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "thedrummer/rocinante-12b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="thedrummer/rocinante-12b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "thedrummer/rocinante-12b",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does Rocinante 12B cost via API?
Through OpenKey, Rocinante 12B costs $0.258 per 1M input tokens and $0.515 per 1M output tokens. That is the provider price ($0.250 / $0.500) plus a flat 3% fee — nothing else.
What is Rocinante 12B's context window?
Rocinante 12B accepts up to 33K tokens of context.
Is Rocinante 12B OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "thedrummer/rocinante-12b" using any OpenAI SDK — only the base URL and API key change.
What inputs does Rocinante 12B support?
Rocinante 12B accepts text input and produces text output. Its knowledge cutoff is Apr 30, 2024.

More from TheDrummer

All TheDrummer models →