Como uso os modelos de Sao10K pela API do OpenRouter?

O OpenRouter disponibiliza 7 modelos de Sao10K por meio de uma única API compatível com a OpenAI. Crie uma chave de API do OpenRouter, aponte seu cliente para https://openrouter.ai/api/v1 e defina o modelo com um ID como sao10k/l3.1-70b-hanami-x1. O guia de início rápido contém exemplos de requisições para cada SDK compatível.

Qual modelo de Sao10K tem a maior janela de contexto?

Llama 3.1 Euryale 70B v2.2 tem a maior janela de contexto entre todos os modelos de Sao10K no OpenRouter, aceitando até 131.072 tokens por solicitação.

Qual é o modelo mais recente de Sao10K no OpenRouter?

Llama 3.1 70B Hanami x1 é o modelo de Sao10K adicionado mais recentemente ao OpenRouter, listado em 8 de janeiro de 2025.

API e modelos de Sao10K

Llama 3.1 70B Hanami x1

This is Sao10K's experiment over Euryale v2.2.

por sao10k16K de contexto

Llama 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.

por sao10k8K de contexto

Llama 3.1 Euryale 70B v2.2

635M 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.

por sao10k131K de contextoUS$ 0,85/M entrada US$ 0,85/M saída

Llama 3 8B Lunaris

4,49B 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.

por sao10k8K de contextoUS$ 0,04/M entrada US$ 0,05/M saída

Llama 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

por sao10k32K de contexto

Llama 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.

por sao10k8K de contexto

Fimbulvetr 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.

por sao10k8K de contexto

Sao10K

Perguntas frequentes

Sao10K

Perguntas frequentes