DeepSeek

DeepSeek-R1

Chinese open-source reasoning model, rivaling o1 in mathematics, coding, and scientific reasoning with exceptional cost-effectiveness

Category Text Model ID deepseek-r1

Context Length64K tokens

Model TypeReasoning Model

Open SourceYes

Pricing & Specs

💰 Pricing

Input¥1.4 / M tokens

Output¥2.8 / M tokens

⚙️ Specs

Context Length64K tokens

Model TypeReasoning Model

Open SourceYes

Special CapabilitiesReinforcement Learning Reasoning

API Examples

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.zairouter.com/v1",
    api_key="your-api-key"
)

response = client.chat.completions.create(
    model="deepseek-r1",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

print(response.choices[0].message.content)

cURL

curl https://api.zairouter.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "deepseek-r1",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Model Features

DeepSeek-R1 is a milestone in Chinese open-source reasoning models, achieving world-class performance across multiple dimensions:

Open Source Advantage: Fully open source, freely available for use and research
Strong Reasoning Capabilities: Rivals OpenAI o1 in mathematics, coding, and other reasoning tasks
Exceptional Cost-effectiveness: Priced at only 1/10 of comparable models
Chinese-friendly: Excellent understanding and generation capabilities for Chinese language

Use Cases

Mathematical problem-solving
Algorithm competitions and programming
Scientific research reasoning
Logic analysis tasks
Education and learning assistance

Performance Advantages

DeepSeek-R1 achieves performance levels comparable to o1 in multiple benchmarks including AIME and Codeforces. As an open-source model, it provides exceptional cost-effectiveness, making it a source of pride for Chinese AI.

← Back to Models