DeepSeek R1

New

by DeepSeek

Reasoning-focused model trained with reinforcement learning for complex tasks.

Parameters
671B MoE
Context Length
64K
Category
chat
Available Serverless

Run queries immediately, pay only for usage

$3.00in|$7.00out

Per 1M Tokens

Try this modelView documentation

About this model

DeepSeek R1 is a breakthrough reasoning model trained with reinforcement learning. It excels at multi-step reasoning, mathematical proofs, and complex logical problems. The model has been specifically optimized to show its reasoning process, making it ideal for tasks requiring transparent decision-making.

Capabilities

Chain-of-ThoughtMathematical ReasoningLogical DeductionProblem Decomposition

Use Cases

  • Math Competition
  • Scientific Research
  • Legal Analysis
  • Strategic Planning

Model Details

Provider
DeepSeek
Model ID
deepseek-ai/DeepSeek-R1
Parameters
671B MoE
Context Length
64K tokens
Category
chat

API Usage

Use the DOS API to integrate DeepSeek R1 into your applications. Our API is compatible with OpenAI's client libraries for easy migration.

Model ID

deepseek-ai/DeepSeek-R1

Python

python
from dos import DOS

client = DOS()

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-R1",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

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

cURL

bash
curl https://api.dos.ai/v1/chat/completions \
  -H "Authorization: Bearer $DOS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-R1",
    "messages": [
      {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Node.js

javascript
import DOS from 'dos-ai';

const client = new DOS();

const response = await client.chat.completions.create({
  model: "deepseek-ai/DeepSeek-R1",
  messages: [
    { role: "user", content: "Hello, how are you?" }
  ]
});

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