deepseek-r1

Neural Network

DeepSeek R1 is an open-source neural network model specializing in mathematics, programming, and logical deduction. It processes up to 128,000 tokens at a time, easing work on large-scale projects and complex calculations. Users gain a powerful tool for quickly solving practical tasks and optimizing processes (DeepSeek Insider, Writesonic).

Main

Models

deepseek-r1

16 000

Max answer length

(in tokens)

64 000

Context size

(in tokens)

82,5 ₽

Prompt cost

(per 1M tokens)

294,64 ₽

Answer cost

(per 1M tokens)

0 ₽

Image prompt

(per 1K tokens)

*Prices for using the API.

Overview

Providers

API

BotHub: Try chat GPT for freebot

Caps remaining: 0 CAPS

Providers deepseek-r1On Bothub, you can select your own providers for requests. If you haven't made a selection, we will automatically find suitable providers who can handle the size and parameters of your request.

Code example and API for deepseek-r1We offer full access to the OpenAI API through our service. All our endpoints fully comply with OpenAI endpoints and can be used both with plugins and when developing your own software through the SDK.Create API key

Javascript

Python

Curl

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: 'deepseek-r1',
  });
} 

// Async - Text generation 

async function main() {
  const stream = await openai.chat.completions.create({
    messages: [{ role: 'user', content: 'Say this is a test' }],
    model: 'deepseek-r1',
    stream: true
  });

  for await (const chunk of stream) {
    const part: string | null = chunk.choices[0].delta?.content ?? null;
  }
} 

main();
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: 'deepseek-r1',
  });
} 

// Async - Text generation 

async function main() {
  const stream = await openai.chat.completions.create({
    messages: [{ role: 'user', content: 'Say this is a test' }],
    model: 'deepseek-r1',
    stream: true
  });

  for await (const chunk of stream) {
    const part: string | null = chunk.choices[0].delta?.content ?? null;
  }
} 
main();

How it works deepseek-r1?

The main benefit is significant time and resource savings. DeepSeek R1 outperforms some models in coding and mathematical tests while maintaining low cost. Thanks to its Mixture of Experts architecture, only a portion of its parameters are activated, reducing strain on equipment. The model integrates easily into local infrastructure and allows flexible functionality expansion via API. Thus, DeepSeek R1 becomes a rational choice for those in search of a powerful, affordable, and scalable tool for solving a wide variety of tasks.