Models / Uncensored / Envoid
Llama 3.05 Storybreaker 70B Ministral API pricing
$1.7255 in, $1.7255 out per million tokens.
Price · per million tokens, USD
Get a key| Tokens | Envoid list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $1.7255 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $1.7255 | — |
Llama 3.05 Storybreaker 70B Ministral specs
- Context window
- 16,384 tokens
- Max output
- 8,192 tokens
- Input
- text
Storybreaker 70B Ministral: Ministral’s roleplay style on a 70B · Envoid’s reverse distillation, tuned for SFW and NSFW roleplay
Llama 3.05 Storybreaker 70B Ministral is Envoid's experiment in reverse distillation: teaching a 70B the roleplay habits of a smaller model (its card, created 2024-10-23). Starting from the Tenyxchat Storybreaker merge, Envoid built a single-turn roleplay set by running SillyTavern-style prompts through Mistral AI's Ministral 8B, trained a rank-16 QLoRA on it with a 0.6 dropout rate (after the very-large-dropout paper, arXiv 2403.00946), merged the adapter in, and SLERP-merged the result back onto the original at 40/60. The card says the model is far more inclined to adult content than its predecessor and was tuned on SFW and NSFW roleplay data, that action flows as a continuous advance rather than a short loop, and that lower temperatures read cleaner. It is served as storybreaker-70b-ministral at $1.7255 input and $1.7255 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.
| Llama 3.05 Storybreaker 70B Ministral | |
|---|---|
| Base model | Llama 3.05 Storybreaker 70B Tenyxchat |
| Made by | Envoid |
| Method | QLoRA on Ministral 8B roleplay outputs, SLERP-merged back at 40/60 |
| License on the card | cc-by-nc-4.0 |
| Context window here | 16,384 tokens |
| Downloads, 30 days to 2026-10-21 | 14 |
| Card | Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B |
From the Hugging Face card and its API record, read 2026-10-21.
The card finds the model stingy with end-of-turn tokens at high temperatures and rigid at low ones, and says lowering the temperature improves the prose.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"storybreaker-70b-ministral","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'Llama 3.05 Storybreaker 70B Ministral 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 Llama 3.05 Storybreaker 70B Ministral: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $1.7255 input and $1.7255 output per million tokens, that is $3.451 + $0.8628 = $4.31, paid from prepaid credit with no subscription.
Llama 3.05 Storybreaker 70B Ministral 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="storybreaker-70b-ministral",
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: 'storybreaker-70b-ministral',
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":"storybreaker-70b-ministral","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 Envoid
Llama 3.05 Storybreaker 70B Ministral questions
- What is Llama 3.05 Storybreaker 70B Ministral?
- Llama 3.05 Storybreaker 70B Ministral is a model from Envoid, with a 16,384-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as storybreaker-70b-ministral.
- How much does the Llama 3.05 Storybreaker 70B Ministral API cost?
- $1.7255 per million input tokens and $1.7255 per million output tokens.
- Is Llama 3.05 Storybreaker 70B Ministral 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 $0.0026.
- What is the Llama 3.05 Storybreaker 70B Ministral context window?
- Llama 3.05 Storybreaker 70B Ministral has a 16,384-token context window, with up to 8,192 output tokens per request. It takes text input.
- What is the Llama 3.05 Storybreaker 70B Ministral model id?
- storybreaker-70b-ministral. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a Llama 3.05 Storybreaker 70B Ministral 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 Llama 3.05 Storybreaker 70B Ministral and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
- Is there a Llama 3.05 Storybreaker 70B Ministral API?
- Yes: storybreaker-70b-ministral on the OpenAI format at https://api.uplinkswitch.com/v1, $1.7255 input and $1.7255 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 Llama 3.05 Storybreaker 70B Ministral based on?
- Envoid’s own Llama 3.05 Storybreaker 70B Tenyxchat (Nemotron 70B with a story-writing tune merged in), with a QLoRA trained on Ministral 8B roleplay outputs merged in and SLERP-blended back at 40/60, per its card.
- What license does Llama 3.05 Storybreaker 70B Ministral have?
- The card lists CC BY-NC 4.0, non-commercial, and tags the model not-for-all-audiences. Its Llama base is under Meta’s Llama 3.1 community license.
- What does Llama 3.05 Storybreaker 70B Ministral cost per 100 messages?
- $0.4314 for 100 chat turns of 2,000 input and 500 output tokens each, at $1.7255 input and $1.7255 output per million tokens, from prepaid credit with no subscription.
- What does reverse distillation mean here?
- Usually a small model learns from a large one. Envoid did the opposite: generated roleplay replies with the 8B Ministral, then trained the 70B on them so it picks up Ministral’s way of moving a scene forward, per the card.
- Llama 3.05 Storybreaker 70B Ministral or Llama 3.05 Storybreaker 70B Tenyxchat?
- The Ministral build is the Tenyxchat merge with the Ministral roleplay QLoRA folded in; the card says it leans much further into adult content and follows a scene more continuously. Llama 3.05 Storybreaker 70B Ministral is $1.7255 / $1.7255 per million tokens in / out, $4.31 for 1,000 chat turns; Llama 3.05 Storybreaker 70B Tenyxchat is $1.7255 / $1.7255 per million tokens in / out, $4.31 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.