ReMM SLERP L2 13B
Neural Network
ReMM SLERP L2 13B is an open 13B parameter language model, recreated from MythoMax L2 13B using the SLERP merging method.
Max answer length
(in tokens)
Context size
(in tokens)
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
How it works ReMM SLERP L2 13B?
ReMM SLERP L2 13B is an open 13B parameter text model born from an experiment: the authors rebuilt the MythoMax L2 13B concept using updated source models merged via SLERP, making this a rebuild rather than a copy. In BotHub, the model is accessible without a VPN or foreign card; pay with Russian cards in rubles only for tokens used, which never expire. Access over 250 models in one window to easily compare responses to the same prompt, and use a single OpenAI-compatible API to switch models without rewriting integrations. Chats are encrypted via AES-GCM, and companies get contracts, invoices, EDI, and an admin panel with limits. It's useful for drafting and rewriting text, summarizing long content, creating dialogue scenarios for bots or assistants, prototyping services via API without vendor lock-in, or comparing how different models handle your tasks.Frequently asked questions about ReMM SLERP 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 text model by undi95: it accepts text, documents, and images as input and responds with text. The context window is 4096 tokens, making it well-suited for dialogues, rewriting and editing phrasing, answering based on short document fragments, and analyzing individual images.
The output limit is 5529 tokens per response. Keep in mind the 4096-token context window: it includes both your prompt and what the model has already written, so it is easier to assemble long materials in parts by continuing the dialogue.
A dedicated reasoning mode is not noted in our data for this model, but that doesn't prevent step-by-step analysis. Ask it directly in the prompt to break down the logic step-by-step and split the task into parts — the quality of the response usually improves significantly.
Function calling and strict structured output are not noted in our data for remm-slerp-l2-13b. You can describe the schema in the prompt and request the response in the desired format, but if you need guarantees, you can switch to another model via the unified OpenAI-compatible BotHub API without rewriting your integration.
The model accepts images and documents as input — these are confirmed capabilities, and it responds with text. Audio and video input is not noted in our data, so for audio and video files, it is better to choose a specialized model from the BotHub catalog.
We do not provide data on prompt and response languages for this model, so we won't invent an assessment — it's easier to test it with your real tasks. In BotHub, this is available without a VPN or foreign card, payment is via Russian cards as you go, and unused tokens do not expire.