MiniMax 01
Neural Network
MiniMax 01 is a multimodal neural network by MiniMax for text generation and image understanding, available via BotHub API.
Max answer length
(in tokens)
Context size
(in tokens)
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
How it works MiniMax 01?
MiniMax 01 is a multimodal model by MiniMax that combines two parts: MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. The architecture has 456 billion parameters, with 45.9 billion activated per request, allowing the model to handle both large texts and visual content confidently. In BotHub, you connect without a VPN or foreign card: payment is made with Russian cards in rubles based on actual token usage, and tokens do not expire. Over 250 models are available in one window, making it easy to switch between them and compare answers for the same task. Developers get a unified OpenAI-compatible API, so there's no need to rewrite integration when switching models. Chats are encrypted, and companies can set up contracts, invoices, and electronic document management with an admin panel and limits. It is useful for analyzing long documents and summarizing them, describing screenshots or diagrams, drafting articles, extracting data from tables in photos, and continuing work with them as text.Frequently asked questions about MiniMax 01
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.
minimax-01 is a text model with a 4,000,000 token context. It accepts text, documents, and images, making it suitable for analyzing large archives, technical documentation, code, and long reports. It is convenient when you need to keep the entire material intact rather than breaking it into parts.
The output limit is 900,172 tokens per response, which is a very large volume for a text model. It is enough for a full document, a detailed analysis, or a large code module in its entirety, without cutting it into fragments. The actual length depends on your request and task.
In our data, a separate reasoning mode for minimax-01 is not noted, but that does not mean it does not exist. In practice, a simple trick helps: ask the model to break down the task step-by-step and show its thought process before the final conclusion. The quality of the answer on complex tasks increases noticeably.
In our data, function calling and strict JSON output for minimax-01 are not marked, so we cannot guarantee them in advance. The easiest way to check is with your own scenario via the unified OpenAI-compatible BotHub API: if the format does not fit, you can switch to another model without rewriting the integration.
Yes, minimax-01 accepts images and documents as input: you can send a screenshot, diagram, photo of a page, or file and ask to analyze the content. Audio and video are not marked as input formats in our data, so for voiceovers or videos, choose a specialized model in the BotHub catalog.
We do not have data on languages, so we will not promise specific quality for Russian — it is fairer to check it with your own task. Open minimax-01 in BotHub without a VPN or foreign card, send a couple of typical requests, and compare the result with another model in the same window.