LLM Reference

4 models across 3 families · Latest: L3.1 70B Euryale V2.2 (2024-08)

Long context

Sao10K's portfolio covers 4 active models across 3 non-obsolete families, with task labels spanning long context. Open a model detail page to compare provider routes and sourced benchmarks.

Portfolio context: 1 decision-task tag, 4 active tracked models, latest research stamp 2026-05-22.

Use this portfolio page for

  • Teams evaluating long context across this lab's releases
  • Readers comparing families before locking a flagship SKU
  • 4 tracked SKUs for migration and pricing follow-ups

Do not stop here for

  • Choosing a hosting provider without opening a model page for price ladders

Active models

4

Non-deprecated SKUs linked to this researcher

Active families

3

Non-obsolete families in coverage

Open catalog

4 OSS

0 open-weight (text match)

Decision task tags

1

Mapped to the site-wide task taxonomy

Latest dated release

2024-08-28

L3.1 70B Euryale V2.2

Freshness

2026-05-22

Researched today

fresh

Release cadence

Showing 4 recent dated ships (full timeline below). Latest spotlight: L3.1 70B Euryale V2.2 (2024-08-28).

Where this lab wins

  • Long-context: 1 tracked model with context-token or InfiniteBench-class signal.

Flagship quality / price signal

Anchor SKU: L3 70B Euryale V2.1 (best sourced coding Q/$ in this portfolio).

Quality / dollar unavailable for this anchor — missing benchmark coverage and/or output token price on the cheapest ladder route (open the model detail after pricing lands).

Sao10K is an AI research organization. Sao10K ships 3 model families totaling 4 models, with the most recent release L3.1 70B Euryale V2.2 in 2024-08. Notable families include Euryale, Lunaris, and Stheno. Use it as a stable reference for lab background, release coverage, and follow-up model pages as they are added. Researchers and evaluators can scan counts, links, release history, and source references without leaving the directory.

About

Sao10K is an independent community model creator specializing in roleplay and creative writing fine-tunes of Meta Llama models. Best known for the Euryale, Stheno, and Lunaris fine-tune series, which are widely used in community roleplay and chat applications.

Featured models

ModelReleasedContextInput price ($/1M)Output price ($/1M)License
L3.1 70B Euryale V2.22024-08-28131072$1.48$1.48Llama 3.1 Community
L3 8B Lunaris2024-06-268192$0.05$0.05Llama 3 Community
L3 70B Euryale V2.12024-06-148192$1.48$1.48Llama 3 Community

Model families

Recent releases

  1. L3.1 70B Euryale V2.2- 2024-08-28
  2. L3 8B Lunaris- 2024-06-26
  3. L3 70B Euryale V2.1- 2024-06-14
  4. L3 8B Stheno V3.2- 2024-06-05

FAQ

What models has Sao10K released?

Sao10K ships 4 models across 3 families: Euryale, Lunaris, and Stheno.

Is Sao10K's technology open source?

All tracked Sao10K models are open-weight or open-source.

How can I access Sao10K's models?

Sao10K's models are available via Novita AI.

Explore related pages

Last reviewed: 2026-05-22. Data sourced from public lab announcements and provider documentation.