All models
T
Thinking Machines
Inkling
Thinking Machines' model: text, images, audio
Text
Images
Audio
Reasoning
Tools
- Type
- Chat
- Context
- 1.0M tokens
- Russian
- medium
- Input price
- 80 ₽ / 1M tokens
- Output price
- 324 ₽ / 1M tokens
- Release date
- July 15, 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: "inkling", messages: [{ role: "user", content: "Hi!" }], stream: true,})for await (const chunk of stream) { process.stdout.write(chunk.choices[0]?.delta?.content ?? "")}About the model
Inkling is a Thinking Machines model that accepts text, images and audio. It supports reasoning on complex tasks and holds a context of up to a million tokens, so it is suited both to long materials and to mixed collections with pictures and recordings. Tool calling (function-calling) is supported, so the model fits into agent scenarios. It follows instructions and keeps the output format. Russian at a medium level.
Strengths
- Text, images and audio as input
- Reasoning for complex tasks
- Context up to 1M tokens
- Tool calling (function-calling)
Where to use it
- Analyzing images and recordings
- Assistants that analyze images
- Analytics on long materials
- Agent scenarios
- Generating and editing text