DeepSeekBalanced

DeepSeek R1

State-of-the-art reasoning model with transparent chain-of-thought. Excels at mathematics, logic, and complex problem decomposition.

4.7(15,600 ratings)

Quick Overview

CategoryReasoning

Context Window128K tokens

SpeedStandard

Input$0.55 / 1M tokens

Output$2 / 1M tokens

Pricing

Simple, transparent token-based pricing. Pay only for what you use.

Input Tokens

$0.55

per 1M tokens

Output Tokens

per 1M tokens

Capabilities

Core strengths and supported features of DeepSeek R1.

Reasoning

Mathematics

Code

Science

Performance

Context window capacity and inference speed characteristics.

Context Window

128K

Standard context window that handles most use cases including document analysis, code review, and lengthy conversations.

Speed: Standard

Balanced speed and quality. Well-suited for production workloads that need a good balance between response quality and latency.

Quick Start

Get started with DeepSeek R1 in just a few lines of code.

import OriginalPoint from "originalpoint";

const client = new OriginalPoint({
  apiKey: process.env.ORIGINALPOINT_API_KEY,
});

const response = await client.chat.completions.create({
  model: "deepseek-r1",
  messages: [
    {
      role: "user",
      content: "Hello, how can you help me today?",
    },
  ],
  max_tokens: 1024,
});

console.log(response.choices[0].message.content);