Yenisei

Yenisei Docs

Scan recognition for PDFs without a text layer

Text

Tools

Type: Chat
Context: 131K tokens
Russian: high
Input price: 16 ₽ / 1M tokens
Output price: 80 ₽ / 1M tokens
Release date: August 2026

chat/completions

import OpenAI from "openai"
const client = new OpenAI({
  baseURL: "https://api.yenisei.ru/v1",
  apiKey: process.env.YENISEI_API_KEY,
})
const stream = await client.chat.completions.create({
  model: "yenisei-doc",
  messages: [{ role: "user", content: "Hi!" }],
  stream: true,
})
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "")
}

About the model

Yenisei Docs reads documents whose text cannot simply be extracted: scans, photos of pages, PDFs without a text layer, and returns the content as text ready for processing. Send a file and get a contract, a certificate or a report back as plain text with its structure preserved. You can call it through the API like any other model in the catalog; the chat and the app call it on their own whenever they encounter a scan.