You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.

This is a fine-tuned model based on Llama 3.1 70B by sao10k, focused on text: dialogues, roleplay scenarios, creative writing, editing, and summarization. You can input not only text but also documents and images, and tool calling allows you to integrate it into workflows.

Up to 16,384 tokens per response — enough for a large chapter, a long scene, or a detailed analysis. Note that the context is 8,192 tokens, so long dialogues and bulky documents should be split into parts or periodically summarized for the model.

A separate reasoning mode is not noted in our data. However, you can ask the model to break down the task step-by-step directly in the prompt — for creative and analytical scenarios, this usually yields a noticeably more coherent and thoughtful result.

Yes, the model supports function calling and structured JSON output. This is convenient when the response needs to be passed directly to your backend, database, or bot script. In BotHub, connection is via a unified OpenAI-compatible API, so you won't have to rewrite integrations when switching models.

You can input images and documents — the model will analyze the content and respond with text. There is no information about audio or video in our data. If you need such files, specialized models for speech recognition and media processing are available nearby in BotHub.

The base Llama 3.1 70B was trained on multilingual data, so the model generally works with Russian text. Quality depends on the task, so it's best to test with your own prompts — in BotHub, you pay per token, without a subscription, and can easily compare results with other models.