Stheno Models by Sao10K
1 model2024Up to 8k ctxFrom $0.050/1M input
Last refreshed 2026-05-22. Next refresh: weekly.
Details
ResearcherSao10K
LicenseLlama 3 Community
Commercial useCommercial use: conditional
Models1
Released2024
Max context8k
Links
HuggingFaceAbout
Stheno is Sao10K's flagship community fine-tune series of Meta Llama 3 8B, trained on curated creative story datasets. Widely used for roleplay and creative writing applications. Consistently ranks highly in community evaluations for multi-turn narrative quality.
Decision facts
- Best fit
- General model comparison
- Capability starting point
- L3 8B Stheno V3.2 with 8k context
- Lowest tracked input
- L3 8B Stheno V3.2 · $0.050/1M · Novita AI
- Closest related family
- Euryale
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
L3 8B Stheno V3.2Current
Use when the workload needs 8k context and 8B parameters.
2024-068k context8B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| L3 8B Stheno V3.2 | Use when the workload needs 8k context and 8B parameters. | 2024-06 | 8k context8B parameters | Current |
Release Timeline
1 release group2024-06
1 current
L3 8B Stheno V3.2
Current8k context8B parameters
Specifications(1 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| L3 8B Stheno V3.2 | 2024-06 | 8k | 8B |
Available From(1 provider)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| L3 8B Stheno V3.2 | Novita AI | $0.05 | $0.05 | Serverless |