Hunyuan A13B Instruct
Neural Network
Hunyuan A13B Instruct is a Tencent MoE language model with step-by-step reasoning, available via API in BotHub
Max answer length
(in tokens)
Context size
(in tokens)
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
How it works Hunyuan A13B Instruct?
Hunyuan A13B Instruct is a Tencent language model based on the Mixture-of-Experts architecture: out of 80 billion parameters, about 13 billion are active per request, combining the knowledge of a large network with efficient generation. The model supports chain-of-thought reasoning and shows competitive results on public benchmarks. In BotHub, it is accessible without a VPN or foreign card: pay with a Russian card in rubles only for used tokens that do not expire. Other models are available in the same window for easy comparison, and a unified OpenAI-compatible API allows switching models without rewriting integrations. Chats are encrypted via AES-GCM, and companies have access to contracts, invoices, EDI, and an admin panel with limits. It is useful for summarizing long documents, solving analytical or STEM tasks step-by-step with visible logic, debugging code, editing text, and comparing answers by running the same prompt through multiple models.Frequently asked questions about Hunyuan A13B Instruct
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 Tencent text model with a reasoning mode. It is suitable for answering questions, analyzing and summarizing documents, working with code, logical and STEM tasks, and writing/editing text. You can input not only text but also images and documents.
The output limit is up to 117,964 tokens, which is enough for voluminous documents, detailed analyses, and long code snippets. The dialogue context is 32,768 tokens, so it is better to submit very large source files in parts and save intermediate results separately.
Yes, the model's reasoning mode is confirmed. Before the final answer, it breaks down the task step-by-step, which significantly helps with math, logic, data analysis, and code debugging. For simple queries, such analysis is usually not needed, and the answer comes faster.
Our data does not indicate support for function calling or structured output, so we cannot guarantee this behavior — please test it in your scenario. BotHub provides a unified OpenAI-compatible API: if you need a model with confirmed tools, you can switch to it without rewriting your integration.
The model accepts images and documents as input: you can ask it to describe an image, extract data from a scan, or analyze file content. Audio and video are not supported according to our data. The model returns text responses — it does not generate images or sound.
The model is multilingual and generally handles Russian queries well, but the quality depends on the specific task. We recommend testing it on your typical scenarios and, if necessary, comparing it with other models in the BotHub window — this can be done in a couple of clicks.