Gigachat 2 Max
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-Max',
});
}
// 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-Max',
stream: true
});
for await (const chunk of stream) {
const part: string | null = chunk.choices[0].delta?.content ?? null;
}
}
main();
How it works Gigachat 2 Max?
Frequently asked questions about Gigachat 2 Max
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-Max works with text: it writes and edits materials, answers questions, helps with code and analytics, and summarizes documents. The 128,000-token context allows you to keep large files, correspondence, or technical documentation in a single dialogue and analyze them in their entirety.
Up to 128,000 tokens in a single response is the upper limit according to our data. The actual length depends on the task and your settings, but there is enough capacity for a voluminous article, a detailed analysis, or a large code fragment without splitting it into parts.
In our data, a separate reasoning mode for this model is not noted, so we will not promise it in advance. However, you can ask it to write out the solution step-by-step directly in the prompt — for complex tasks, this usually significantly improves the quality of the answer.
There is no mention of function calling or strict JSON mode in the model card, so you shouldn't rely on them in advance. You can always ask for a response in JSON format directly in the prompt, and it is easier to check the behavior with tools via a test request through our API.
The model is declared as text-only: the reception of images, audio, and video is not noted in our data. File content can be transmitted as text — the 128,000-token context allows for this. If you need to work with images or sound, specialized models are available nearby in BotHub.
GigaChat is a Russian development, and Russian is its native language: the model confidently handles grammar, cases, and business style, and understands local realities and terminology. In BotHub, it is available without a VPN or foreign card, with payment in rubles based on actual usage.