Specifications
- Input
- text
- Output
- text
- Context size
- 128 000 tokens
- Max answer length
- 128 000 tokens
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
Image prompt
(per 1K tokens)
import OpenAI from 'openai';
const openai = new OpenAI({
apiKey: '<your bothub access token>',
baseURL: 'https://openai.bothub.chat/v1'
});
// Sync - Text generation
async function main() {
const chatCompletion = await openai.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'GigaChat-Pro',
});
}
// Async - Text generation
async function main() {
const stream = await openai.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'GigaChat-Pro',
stream: true
});
for await (const chunk of stream) {
const part: string | null = chunk.choices[0].delta?.content ?? null;
}
}
main();
How it works GigaChat-Pro?
Frequently asked questions about GigaChat-Pro
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.
GigaChat-Pro is a text model from GigaChat: text in, text out. It is suitable for business correspondence, articles and descriptions, summarizing and structuring documents, answering questions based on uploaded materials, and assisting with code. The context window is 128,000 tokens, so long documents can be analyzed in their entirety.
According to our data, the output limit is 128,000 tokens per response, the same as the context window. This is enough for a voluminous document, a detailed analysis, or a large code fragment without splitting it into parts. The actual length depends on how detailed a result you requested.
A separate reasoning mode for GigaChat-Pro is not noted in our data, but that does not mean it does not exist. If a task requires a step-by-step analysis, ask for it directly in the prompt: the model will break down the solution into steps within the response itself, and you will see the entire logic.
There is no mention of function calling or structured JSON output in our data, so we will not promise them. Test it with your scenario via the unified OpenAI-compatible BotHub API: if the format does not fit, switch to another model without rewriting the integration.
In our data, GigaChat-Pro is described as a text model; input of other formats is not noted. If you need to work with images, audio, or video, select a specialized model in BotHub: switching takes a couple of seconds and happens in the same window.
GigaChat-Pro is a development by the Russian GigaChat team, and Russian is a priority for it: the model accurately maintains grammar and cases, senses business tone, and understands domestic context and realities. This is especially noticeable in editing, summarizing, and official letters. For your tasks, it is worth checking the result with a few prompts.