DeepSeek R1 Zero

About DeepSeek R1 Zero

DeepSeek-R1-Zero is a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step. It's 671B parameters in size, with 37B active in an inference pass. It demonstrates remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. See [DeepSeek R1](/deepseek/deepseek-r1) for the SFT model.

Model Specifications

DeepSeek Model Lineup

Compare all models from DeepSeek to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Gemma 3n 4B

Google

Input: Free

Output: Free

Context: 33k

Qwen2.5-VL 7B Instruct

Alibaba Qwen

Input: Free

Output: Free

Context: 33k

Seedream 4.5

ByteDance

Input: Free

Output: Free

Context: 4k

FLUX.2 Max

Black Forest Labs

Input: Free

Output: Free

Context: 47k

🚀 Quick Start

Get started with DeepSeek R1 Zero API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="deepseek/deepseek-r1-zero",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision