Weaver
Neural Network
Weaver is a text AI for roleplay and creative writing: expansive, detailed responses for interactive storytelling.
Max answer length
(in tokens)
Context size
(in tokens)
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
How it works Weaver?
Weaver is a text model for creative and roleplay scenarios: it provides expansive, detailed descriptions of scenes, dialogue, and details, designed specifically for interactive storytelling. Its coherence and context retention are more modest than its verbosity, so it works best in short episodes with periodic context reminders. In BotHub, the model is accessible without a VPN or foreign card: pay with Russian cards in rubles only for tokens used, with no subscription. Over 250 models are available in one window—you can draft a scene with one and edit with another. For products, there is a unified OpenAI-compatible API, chats are encrypted via AES-GCM, and companies have access to contracts, invoices, and an admin panel with limits. It is useful if you are running an interactive branching story, collecting character lines and traits for a game, drafting dialogue and location descriptions for prose or scripts, or looking for several variations of a scene in different tones.Frequently asked questions about Weaver
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.
Weaver is a text model that works with more than just text: you can input documents and images. It is suitable for drafting and editing, summarizing and structuring, analyzing contracts and reports, and answering questions about file or screenshot content. In BotHub, the model is available without a VPN or foreign card.
The single response limit is up to 6,000 tokens, with a total context window of 8,000 tokens. In practice, this means it is better to request long articles or large reports in parts: first the plan, then the sections. This way, you won't hit the response limit.
A separate reasoning mode for Weaver is not noted in our data, so we won't promise it. However, you can request a step-by-step breakdown directly in your prompt: ask it to write out the logic first, then the conclusion. This significantly helps with complex tasks.
Function calling and strict JSON output are not noted in our data — please test with your scenario. You can request a JSON-formatted response with a standard prompt. If you need guaranteed tool calling, you can switch to another model via the unified OpenAI-compatible BotHub API without rewriting your integration.
Images and documents — yes, these are confirmed input formats: upload a scan, screenshot, or file and ask questions about the content. Audio and video are not noted in our data, so for voiceovers or recording analysis, it is better to choose a specialized model in BotHub.
We have not measured the quality of Russian, and it is not recorded in the model data, so we won't make precise promises — it is easier to test with your own text. The BotHub interface is in Russian, payment is via ruble card, and access is without VPN; you can compare Weaver with other models in one window in a couple of minutes.