L3 8B Stheno V3.2 is Sao10K's creative writing and roleplay model, fine-tuned on Llama 3 with 8 billion parameters and an 8K context window. It was trained across multiple runs totaling roughly 24 hours on a single H100 SXM, and balances SFW and NSFW handling more evenly than earlier versions while improving prompt and instruction adherence. Sao10K 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. The model holds character consistency across extended interactions, keeping personas true to their definitions over many turns. It is a lighter, more specialized creative tool than the Lunaris merge, and more focused than the 70B Euryale models. It fits roleplay platforms, interactive fiction engines, and creative writing assistants where personality and narrative coherence matter most.
L3 8B Stheno V3.2 runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| US | No | $0.05 | $0.05 |
L3 8B Stheno V3.2 runs on a single route through the Opper gateway today, so its availability is that provider's availability.
Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider Opper monitors.
Each route hosting L3 8B Stheno V3.2 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; SCCs; DPA available.
Call L3 8B Stheno V3.2 through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "novita/Sao10K/L3-8B-Stheno-v3.2",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
