GigaChat-Plus
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-Plus',
});
}
// Async - Text generation
async function main() {
const stream = await openai.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'GigaChat-Plus',
stream: true
});
for await (const chunk of stream) {
const part: string | null = chunk.choices[0].delta?.content ?? null;
}
}
main();
How it works GigaChat-Plus?
Frequently asked questions about GigaChat-Plus
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-Plus works with text: it answers questions, writes and edits materials, analyzes documents, helps with code, and structures information. A 128,000-token context allows you to keep long contracts, reports, or correspondence in a single dialogue and work with them in their entirety without breaking them into pieces.
Up to 128,000 tokens per response — the same as the entire context. This is enough for a voluminous document in its entirety: a chapter, a technical manual, or a large analysis. Keep in mind that the window is shared: the longer the request, the less space remains for the response.
A separate step-by-step reasoning mode is not marked in our data, so we will not promise it. In practice, you can get a step-by-step analysis directly in the prompt: ask the model to first write out the conditions and the solution process, and provide the final conclusion at the end.
In our data, function calling and strict structured output are not marked for this model, so for production, check the behavior in your scenarios. You can define the JSON schema directly in the request and validate the result on your side. Access is via the unified OpenAI-compatible BotHub API.
The confirmed operating mode is text input and text output; the reception of images, audio, and video is not marked in our data. If you need image analysis or recording transcription, switch to a suitable multimodal model in the same BotHub window — you won't have to rewrite the integration.
GigaChat is a Russian development, and Russian-language tasks are its primary focus: phrasing, grammatical cases, business and conversational styles come naturally to it. Plus, access from Russia without a VPN and payment with Russian cards. The best way to verify is to run your typical texts through BotHub and compare them with other models.