deepseek-ai/DeepSeek-R1-Distill-Llama-70B

Created 1/22/2025

deepseek-ai

$0.72 / M Tokens

LeasableThis model is available to lease. It is not currently live, but you can request access to it and will become live shortly if the immunity period of the other models is over.

We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors. However, DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. To address these issues and further enhance reasoning performance, we introduce DeepSeek-R1, which incorporates cold-start data before RL. DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. To support the research community, we have open-sourced DeepSeek-R1-Zero, DeepSeek-R1, and six dense models distilled from DeepSeek-R1 based on Llama and Qwen. DeepSeek-R1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.

Text Generation

Code Examples

Get started with code samples in your preferred language

Chat Example

Basic example of chat with the selected model

curl

1curl https://api.targon.com/v1/chat/completions \
2  -H "Content-Type: application/json" \
3  -H "Authorization: Bearer YOUR_API_KEY" \
4  -N \
5  -d '{
6    "model": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
7    "stream": true,
8    "messages": [
9      {"role": "system", "content": "You are a helpful programming assistant."},
10      {"role": "user", "content": "Write a bubble sort implementation in Python with comments explaining how it works"}
11    ],
12    "temperature": 0.7,
13    "max_tokens": 256,
14    "top_p": 0.1,
15    "frequency_penalty": 0,
16    "presence_penalty": 0
17  }'

Completions Example

Basic example of completions with the selected model

curl

1curl https://api.targon.com/v1/completions \
2    -H "Content-Type: application/json" \
3    -H "Authorization: Bearer YOUR_API_KEY" \
4    -N \
5    -d '{
6      "model": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
7      "stream": true,
8      "prompt": "The x y problem is",
9      "temperature": 0.7,
10      "max_tokens": 256,
11      "top_p": 0.1,
12      "frequency_penalty": 0,
13      "presence_penalty": 0
14    }'