Run Stheno 8B v3.2 without a GPU.

Roleplay by Sao10K, on Unrestrictable as stheno-8b-v3.2.

Stheno 8B v3.2 is Sao10K's roleplay model. It costs $0.7035 per million input tokens and $0.7035 per million output tokens, prepaid, with a 16,384-token context window. Call it at https://api.unrestrictable.ai/v1/chat/completions with model "stheno-8b-v3.2" and an Unrestrictable key, from any OpenAI SDK or client that takes a base URL.

Chat with Stheno 8B v3.2 in the browser, no key: open the chat.

Get a key

Price per million tokens

Input
$0.7035
Cached input
$0.7035 (input rate)
Output
$0.7035
Daily check
Changed Nov 14
As of
2026-11-16

First request

curl
1curl https://api.unrestrictable.ai/v1/chat/completions \
2 -H "Authorization: Bearer sk-unr-live-…" \
3 -H "Content-Type: application/json" \
4 -d '{"model": "stheno-8b-v3.2", "messages": [{"role": "user", "content": "Hello"}]}'

Base URL https://api.unrestrictable.ai/v1. The key comes from the console; prices settle per token.

Stheno 8B v3.2 settings for SillyTavern and Janitor AI

SillyTavern API
Chat Completion
Source
Custom (OpenAI-compatible)
Custom endpoint
https://api.unrestrictable.ai/v1
Model
stheno-8b-v3.2
Context Size
16,384 tokens
Max response length
8,192 tokens
Janitor AI proxy URL
https://api.unrestrictable.ai/v1/chat/completions
Key prefix
sk-unr-

Stheno 8B v3.2 specs

Kind
Roleplay
Developer
Sao10K
Context window
16,384 tokens
Max output
8,192 tokens
Input
text
Wire formats
openai

Get a key

  1. Create a key in the console. Credit is prepaid from $10, with no subscription.
  2. Set OPENAI_BASE_URL to https://api.unrestrictable.ai/v1 and send your sk-unr- key as the bearer token.
  3. Send stheno-8b-v3.2 as the model. The same key calls every model on Unrestrictable.

What Stheno 8B v3.2 is

Base model
Made by
Sao10K
Method
Fine-tune, sixth iteration, merged back to its base
License on the card
cc-by-nc-4.0
Downloads, 30 days to 2026-10-20
5,460
Context window here
16,384 tokens
Max output
8,192 tokens
Input
text

From the Hugging Face card and its API record, read 2026-10-20.

From the SDK

openai.py
1from openai import OpenAI
2
3client = OpenAI(base_url="https://api.unrestrictable.ai/v1", api_key="sk-unr-live-…")
4
5completion = client.chat.completions.create(
6 model="stheno-8b-v3.2",
7 messages=[{"role": "user", "content": "Hello"}],
8)
9print(completion.choices[0].message.content)
openai.ts
1import OpenAI from 'openai';
2
3const client = new OpenAI({ baseURL: 'https://api.unrestrictable.ai/v1', apiKey: 'sk-unr-live-…' });
4
5const completion = await client.chat.completions.create({
6 model: 'stheno-8b-v3.2',
7 messages: [{ role: 'user', content: 'Hello' }],
8});
9console.log(completion.choices[0].message.content);

Guides: SillyTavern, Janitor AI, SDKs.

What Stheno 8B v3.2 is built to write

Stheno 8B v3.2 is a fiction fine-tune: trained on long-form stories and character dialogue, it holds a character's voice, follows a scenario and writes at length without the stock refusal layer.

Every request is routed to the build’s live route and settled to the token at the prices above. The daily real-model check sends a fixed prompt to every model and records whether the answer still matches; this model’s verdict today is “Changed Nov 14”.

Use it from the OpenAI SDK, from SillyTavern or Janitor, or from a coding agent. Keys and top-ups live in the console.

Also try

More from Sao10K

What Stheno 8B v3.2 costs, worked

A chat turn of 2,000 input and 500 output tokens at $0.7035 input and $0.7035 output per million tokens is $0.0018; 1,000 turns are $1.76. A long chat session of 100 replies of 300 tokens costs $0.3025 at 4,000 tokens of context and $1.1467 at 16,000: every message resends the context, so size it to what the chat needs. All from prepaid credit, no subscription.

Roleplay buildsContextIn / out per 1M1,000 chat turns
Manta Flash 1.016K$0.07 / $0.56$0.42
Manta Mini 1.08K$0.07 / $0.56$0.42
Gemma 4 12B Starry Ocean131K$0.175 / $0.875$0.79
Gemma 4 12B StationKeeper131K$0.175 / $0.875$0.79
Magidonia 24B v4.333K$0.3535 / $0.4235$0.92
MythoMax L2 13B4K$0.404 / $0.404$1.01
Cydonia 24B v233K$0.4012 / $0.4828$1.04
Gemma 4 31B Split-Untied262K$0.35 / $1.05$1.23
Cydonia 24B v4.3131K$0.484 / $0.60$1.27
Manta Pro 1.066K$0.21 / $1.75$1.30
Artemis v1.1262K$0.35 / $1.575$1.49
Gemma 4 31B Gembrain262K$0.35 / $1.575$1.49
Gemma 4 31B Isometry262K$0.35 / $1.575$1.49
Qwen3.8 27B Synthia262K$0.35 / $2.10$1.75
Stheno 8B v3.216K$0.7035 / $0.7035$1.76
Qwen3.8 27B DarkIdol262K$0.40 / $2.40$2.00

Live from the catalog on 2026-11-16, ordered by the cost of 1,000 turns of 2,000 input and 500 output tokens. Every model.

Stheno 8B v3.2 in SillyTavern and Janitor AI: what to set

The three fields are the base URL, the key and the model id, as in the settings above. What differs by build is the reply length, the reasoning switch and the context size, and those decide both whether a reply arrives whole and what each message costs.

  • Context Size up to 16,384 tokens, the window the catalog lists for stheno-8b-v3.2. Every message resends the context, so set it to what the chat needs rather than the maximum.
  • A fiction tune answers at once, with no reasoning step: a Max Response Length of 300 to 600 tokens fits a chat reply.

A request that fails before the model answers is not billed. A refusal written as ordinary text is billed like any answer, which is the reason to send this build rather than a stock model with a preamble: the build does not write one.

What Stheno 8B v3.2 costs by client

SessionWhat is sentAt the live price
SillyTavern or Janitor AI, one evening100 replies of 300 tokens on 4,000 tokens of context$0.3025
The same evening on a long chat100 replies of 300 tokens on 16,000 tokens of context$1.1467
A month of short turns1,000 turns of 2,000 input and 500 output tokens$1.7588

Input and output tokens at the price above, read from the catalog on 2026-11-16, with no prompt caching assumed; cached input bills at the cached rate, or at the input rate on a model without one. The balance is prepaid and each request settles at these rates.

Stheno 8B v3.2 questions

Stheno 8B v3.2 is a roleplay build from Sao10K, with a 16,384-token context window, taking text input. On Unrestrictable it answers as stheno-8b-v3.2.

No. Credit is prepaid from $10 and billed per token: input $0.7035 and output $0.7035 per million tokens, cached input $0.7035 (input rate).

About $0.0011 for 1,000 tokens in and 500 tokens out, at $0.7035 in and $0.7035 out per million tokens.

Up to 16,384 tokens, the context window the catalog lists for Stheno 8B v3.2; Max Response Length can go up to 8,192 tokens.

Yes. Send stheno-8b-v3.2 as the model through the OpenAI SDK, or any client that takes a custom OpenAI base URL, with base URL https://api.unrestrictable.ai/v1.

In SillyTavern, set API to Chat Completion, Source to Custom (OpenAI-compatible) and the custom endpoint to https://api.unrestrictable.ai/v1, paste your key, then pick stheno-8b-v3.2 from the list it loads. In Janitor AI, choose Proxy, set the URL to https://api.unrestrictable.ai/v1/chat/completions, paste your key and type stheno-8b-v3.2 as the model. See the docs.

Llama 3 8B (the L3-8B in its repo name; the card uses the Llama 3 Instruct template), fine-tuned by Sao10K on story-writing, Claude 3 Opus instruct and filtered roleplay data, per its card.

The card lists CC BY-NC 4.0.

Yes, the weights are on Hugging Face (Sao10K/L3-8B-Stheno-v3.2, cc-by-nc-4.0, read 2026-10-20). Sending stheno-8b-v3.2 to https://api.unrestrictable.ai/v1 needs no download and no GPU: 100 replies cost $0.3025 at the live price.

$0.1759 for 100 chat turns of 2,000 input and 500 output tokens each, at $0.7035 input and $0.7035 output per million tokens, from prepaid credit with no subscription.

Yes, with the settings above: Chat Completion with a Custom (OpenAI-compatible) source and https://api.unrestrictable.ai/v1 as the endpoint in SillyTavern; the proxy URL https://api.unrestrictable.ai/v1/chat/completions and stheno-8b-v3.2 as the model in Janitor AI. See the SillyTavern guide.

Read next

Join on Telegram