MythoMax L2 13B
Neural Network
MythoMax L2 13B is a text model based on Llama 2 13B for rich descriptions and roleplay dialogues in BotHub.
Max answer length
(in tokens)
Context size
(in tokens)
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
How it works MythoMax L2 13B?
MythoMax L2 13B is a fine-tuned version of Llama 2 13B, created by merging several fine-tunes. This results in a recognizable writing style: detailed, rich descriptions and consistent behavior in roleplay scenarios where maintaining character and scene tone is crucial. The 13-billion parameter model remains one of the most popular Llama 2-based builds precisely because of this combination. In BotHub, it works without a VPN or foreign card: you pay in rubles only for the tokens used, not for a subscription, and the balance does not expire. In the next tab, there are over 250 models to easily switch between and compare responses to the same prompt. A unified OpenAI-compatible API allows you to connect MythoMax to your service and later replace it with any other model without rewriting the integration. Chats are encrypted via AES-GCM. It is useful for authors drafting prose and developing scenes, game designers for NPC lines and location descriptions, interactive story and text adventure teams, chatbot developers, and anywhere rich, descriptive language is needed.Frequently asked questions about MythoMax L2 13B
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 13-billion parameter model by Gryphe, created by merging several Llama 2 variants. Its profile is coherent creative text: stories, dialogues, descriptions, scene sketches, drafts, and idea generation. It also accepts documents and images as input to analyze their content and describe them in text.
The single response limit is 3686 tokens, which is several pages of coherent text. The total context window is 4096 tokens, shared between your prompt and the response, so it is better to process long scenes and large documents in parts.
A dedicated reasoning mode is not noted in our data, so the model answers immediately. You can ask it to break down the solution step-by-step directly in your prompt. If you need long reasoning chains and STEM tasks, switch to a suitable model in the same BotHub window.
Function calling and guaranteed structured output are not noted in our data, so relying on them for production scenarios is risky. You can describe the required schema in the prompt and verify it with a validator on your side. For reliable function calling, use a different model via the same OpenAI-compatible API.
You can upload images and documents: the model will analyze them and respond with text. Audio and video are not among the supported input formats. mythomax-l2-13b generates only text, but for images, voiceovers, and video, BotHub has specialized models in the same interface.
We do not have quality measurements by language and will not promise results — it is more reliable to test it on your specific task. It is easy to do: payment is per token used, they do not expire, and access works without a VPN or foreign card. There are alternatives nearby in the same window for comparison.