Models / Uncensored / Sao10K
Stheno 8B v3.2 API pricing
$0.7035 in, $0.7035 out per million tokens.
Price · per million tokens, USD
Get a key| Tokens | Sao10K list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $0.7035 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $0.7035 | — |
Stheno 8B v3.2 specs
- Context window
- 16,384 tokens
- Max output
- 8,192 tokens
- Input
- text
Stheno 8B v3.2: Sao10K’s Llama 3 8B roleplay model · the small Sao10K model, per token
Stheno 8B v3.2 is Sao10K's Llama 3 8B roleplay and story model (its card, created 2024-06-05, with 5,460 Hugging Face downloads in the 30 days to 2026-10-20). The card says it is the sixth of several training runs merged back to the base at different weights, about 24 hours on one H100 in all. Over v3.1 it added SFW and NSFW story-writing data and more instruct data, and further cleaned its roleplay samples; the card reports better storywriting, multi-turn coherency and instruction adherence. It is served as stheno-8b-v3.2 at $0.7035 input and $0.7035 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.
| Stheno 8B v3.2 | |
|---|---|
| Base model | Llama 3 8B |
| Made by | Sao10K |
| Method | Fine-tune, sixth iteration, merged back to its base |
| License on the card | cc-by-nc-4.0 |
| Context window here | 16,384 tokens |
| Downloads, 30 days to 2026-10-20 | 5,460 |
| Card | Sao10K/L3-8B-Stheno-v3.2 |
From the Hugging Face card and its API record, read 2026-10-20.
The card recommends temperature 1.12 to 1.22, min_p 0.075, top_k 50 and repetition penalty 1.1, with the Llama 3 Instruct template.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"stheno-8b-v3.2","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'Stheno 8B v3.2 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 Stheno 8B v3.2: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $0.7035 input and $0.7035 output per million tokens, that is $1.407 + $0.3518 = $1.76, paid from prepaid credit with no subscription.
Stheno 8B v3.2 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="stheno-8b-v3.2",
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: 'stheno-8b-v3.2',
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":"stheno-8b-v3.2","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 Sao10K
Stheno 8B v3.2 questions
- What is Stheno 8B v3.2?
- Stheno 8B v3.2 is a model from Sao10K, with a 16,384-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as stheno-8b-v3.2.
- How much does the Stheno 8B v3.2 API cost?
- $0.7035 per million input tokens and $0.7035 per million output tokens.
- Is Stheno 8B v3.2 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 $0.0011.
- What is the Stheno 8B v3.2 context window?
- Stheno 8B v3.2 has a 16,384-token context window, with up to 8,192 output tokens per request. It takes text input.
- What is the Stheno 8B v3.2 model id?
- stheno-8b-v3.2. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a Stheno 8B v3.2 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 Stheno 8B v3.2 and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
- Is it the real Stheno 8B v3.2?
- Every day each model gets the same test prompt, and a model always counts that prompt the same way; a swapped one would not. Stheno 8B v3.2's latest result: Same fingerprint since Oct 21, no answer since Oct 22.
- Is there a Stheno 8B v3.2 API?
- Yes: stheno-8b-v3.2 on the OpenAI format at https://api.uplinkswitch.com/v1, $0.7035 input and $0.7035 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 Stheno 8B v3.2 based on?
- 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.
- What license does Stheno 8B v3.2 have?
- The card lists CC BY-NC 4.0.
- What does Stheno 8B v3.2 cost per 100 messages?
- $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.
- What settings does Stheno 8B v3.2 use?
- Its card recommends temperature 1.12 to 1.22, min_p 0.075, top_k 50 and repetition penalty 1.1, and the Llama 3 Instruct template, which the API applies to the messages you send.
- Is there a Stheno API with no subscription?
- Yes: stheno-8b-v3.2 at $0.7035 input and $0.7035 output per million tokens, from prepaid credit with no subscription. 100 chat turns of 2,000 input and 500 output tokens cost $0.1759.
- Stheno 8B v3.2 or Euryale 70B v2.2?
- Both are Sao10K’s: Stheno v3.2 is the Llama 3 8B model, Euryale v2.2 the Llama 3.1 70B one. Stheno 8B v3.2 is $0.7035 / $0.7035 per million tokens in / out, $1.76 for 1,000 chat turns; Euryale 70B v2.2 is $1.224 / $1.428 per million tokens in / out, $3.16 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.