Models / Uncensored / Sao10K
Euryale 70B v2.3 API pricing
$1.479 in, $1.479 out per million tokens.
Price · per million tokens, USD
| Tokens | Sao10K list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $1.479 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $1.479 | — |
Euryale 70B v2.3 specs
- Context window
- 20,480 tokens
- Input
- text
Euryale 70B v2.3: Sao10K’s Llama 3.3 roleplay model · trained on Llama 3.3 70B Instruct, per token
Euryale 70B v2.3 is Sao10K's roleplay and creative-writing model, trained on top of Meta's Llama 3.3 70B Instruct (its card). The card calls it the direct successor to Euryale v2.2 and says it is trained in full, not LoRA-extracted. It is served as euryale-70b-v2.3 at $1.479 input and $1.479 output per million tokens, one of 49 builds in the uncensored LLM API, on the same key as every other model. Added 2026-10-20.
| Euryale 70B v2.3 | |
|---|---|
| Base model | Llama 3.3 70B Instruct |
| Made by | Sao10K |
| Method | Full fine-tune (not LoRA-extracted) |
| License on the card | llama3 |
| Context window here | 20,480 tokens |
| Downloads, 30 days to 2026-10-20 | 1,038 |
| Card | Sao10K/L3.3-70B-Euryale-v2.3 |
From the Hugging Face card and its API record, read 2026-10-20.
The card recommends temperature 1.1 and min_p 0.1, and says the system prompt matters more.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"euryale-70b-v2.3","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'Euryale 70B v2.3 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 Euryale 70B v2.3: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $1.479 input and $1.479 output per million tokens, that is $2.958 + $0.7395 = $3.70, paid from prepaid credit with no subscription.
Euryale 70B v2.3 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="euryale-70b-v2.3",
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: 'euryale-70b-v2.3',
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":"euryale-70b-v2.3","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
Euryale 70B v2.3 questions
- What is Euryale 70B v2.3?
- Euryale 70B v2.3 is a model from Sao10K, with a 20,480-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as euryale-70b-v2.3.
- How much does the Euryale 70B v2.3 API cost?
- $1.479 per million input tokens and $1.479 per million output tokens.
- Is Euryale 70B v2.3 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 $0.0022.
- What is the Euryale 70B v2.3 context window?
- Euryale 70B v2.3 has a 20,480-token context window. It takes text input.
- What is the Euryale 70B v2.3 model id?
- euryale-70b-v2.3. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a Euryale 70B v2.3 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 Euryale 70B v2.3 and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
- Is there a Euryale 70B v2.3 API?
- Yes: euryale-70b-v2.3 on the OpenAI format at https://api.uplinkswitch.com/v1, $1.479 input and $1.479 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 Euryale 70B v2.3 based on?
- Meta’s Llama 3.3 70B Instruct. Sao10K trained Euryale v2.3 on top of it in full, as the successor to v2.2 (which is Llama 3.1 70B), per its card.
- What license does Euryale 70B v2.3 have?
- The card’s license tag is llama3, the Llama community license it inherits from Llama 3.3 70B.
- What does Euryale 70B v2.3 cost per 100 messages?
- $0.3698 for 100 chat turns of 2,000 input and 500 output tokens each, at $1.479 input and $1.479 output per million tokens, from prepaid credit with no subscription.
- What settings does Euryale 70B v2.3 use?
- Its card recommends temperature 1.1 and min_p 0.1, and adds that the system prompt matters more than the samplers.
- Euryale 70B v2.3 or Euryale 70B v2.2?
- v2.3 is trained on Llama 3.3 70B Instruct and is the successor; v2.2 is the Llama 3.1 70B version. Euryale 70B v2.3 is $1.479 / $1.479 per million tokens in / out, $3.70 for 1,000 chat turns; Euryale 70B v2.2 is $0.918 / $1.071 per million tokens in / out, $2.37 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.