How do I use Sao10K models through the OpenRouter API?

OpenRouter serves 7 Sao10K models behind one OpenAI-compatible API. Create an OpenRouter API key, point your client at https://openrouter.ai/api/v1, and set the model to an ID such as sao10k/l3.1-70b-hanami-x1. The quickstart has request examples for every supported SDK.

Which Sao10K model has the largest context window?

Llama 3.1 Euryale 70B v2.2 has the largest context window of any Sao10K model on OpenRouter, accepting up to 131,072 tokens per request.

What is the newest Sao10K model on OpenRouter?

Llama 3.1 70B Hanami x1 is the most recently added Sao10K model on OpenRouter, listed on January 8, 2025.

Sao10K

Access 7 Sao10K models through the OpenRouter unified API including Llama 3.1 70B Hanami x1, Llama 3.3 Euryale 70B, and Llama 3.1 Euryale 70B v2.2. Compare pricing, context windows, benchmarks, and capabilities between different Sao10K models.

Sao10K tokens processed on OpenRouter

Sao10K: Llama 3.1 70B Hanami x1Llama 3.1 70B Hanami x1
This is Sao10K's experiment over Euryale v2.2.
by sao10kJan 8, 202516K context
Sao10K: Llama 3.3 Euryale 70BLlama 3.3 Euryale 70B
Euryale L3.3 70B is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.2.
by sao10kDec 18, 20248K context
Sao10K: Llama 3.1 Euryale 70B v2.2Llama 3.1 Euryale 70B v2.2
597M tokens
Euryale L3.1 70B v2.2 is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.1.
by sao10kAug 28, 2024131K context$0.85/M input tokens$0.85/M output tokens
Sao10K: Llama 3 8B LunarisLlama 3 8B Lunaris
5.21B tokens
Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge. Created by Sao10k, this model aims to offer an improved experience over Stheno v3.2, with enhanced creativity and logical reasoning. For best results, use with Llama 3 Instruct context template, temperature 1.4, and min_p 0.1.
by sao10kAug 13, 20248K context$0.04/M input tokens$0.05/M output tokens
Sao10K: Llama 3 Stheno 8B v3.3 32KLlama 3 Stheno 8B v3.3 32K
Stheno 8B 32K is a creative writing/roleplay model from Sao10k. It was trained at 8K context, then expanded to 32K context. Compared to older Stheno version, this model is trained on: - 2x the amount of creative writing samples - Cleaned up roleplaying samples - Fewer low quality samples
by sao10kJun 27, 202432K context
Sao10k: Llama 3 Euryale 70B v2.1Llama 3 Euryale 70B v2.1
Euryale 70B v2.1 is a model focused on creative roleplay from Sao10k. - Better prompt adherence. - Better anatomy / spatial awareness. - Adapts much better to unique and custom formatting / reply formats. - Very creative, lots of unique swipes. - Is not restrictive during roleplays.
by sao10kJun 18, 20248K context
Fimbulvetr 11B v2Fimbulvetr 11B v2
Creative writing model, routed with permission. It's fast, it keeps the conversation going, and it stays in character. If you submit a raw prompt, you can use Alpaca or Vicuna formats.
by sao10kApr 21, 20248K context

Sao10K

Frequently asked questions

How do I use Sao10K models through the OpenRouter API?

Which Sao10K model has the largest context window?

What is the newest Sao10K model on OpenRouter?