GigaChat-2-Pro
Neural Network
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-2-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-2-Pro',
stream: true
});
for await (const chunk of stream) {
const part: string | null = chunk.choices[0].delta?.content ?? null;
}
}
main();
How it works GigaChat-2-Pro?
Frequently asked questions about GigaChat-2-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-2-Pro is a text model from GigaChat for meaningful language work: long texts and editing, document summaries, answering questions, coding assistance, and logic analysis. The 128,000-token context window allows you to keep voluminous materials in a single dialogue. In BotHub, the model is available without a VPN or foreign card.
The output limit is up to 128,000 tokens per response, the same as the context window. In practice, this is enough for a book chapter, a detailed technical analysis, or a large set of instructions without having to split the task into parts.
A separate reasoning mode is not noted in our data, but that does not mean it does not exist. If a task requires step-by-step logic, ask the model to write out the solution step-by-step — this technique works even without a special mode. It is convenient to compare the result with another model in the same BotHub window.
There is no note about function calling and strict JSON output in our data, so we cannot guarantee the behavior. It is easiest to check in practice: BotHub provides a unified OpenAI-compatible API, so the request is sent with the same code as for other models, and the response schema should be tested on your scenarios.
According to our data, GigaChat-2-Pro works in 'text-in, text-out' mode; acceptance of other formats is not noted. If you need to analyze an image, transcribe a recording, or describe a video, switch to a model with the appropriate modality in the same BotHub interface.
GigaChat is a Russian development, and Russian is its main working language: the model is accustomed to cases, business correspondence, and terminology from domestic documents. Check it with your own texts — you can compare the answer with another model in one window, payment is in rubles, no VPN is needed.