Skip to content
OpenKey

R1 Distill Llama 70B

DeepSeekReleased Jan 23, 2025

DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...

Try in playground
Context window
128K tokens
Max output
8K tokens
Input
text
Output
text
Tokenizer
Llama3
Knowledge cutoff
Jul 31, 2024
Released
Jan 23, 2025
Reasoning
optional

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$0.800$0.024$0.824
Output$0.800$0.024$0.824

Supported parameters

  • frequency_penalty
  • include_reasoning
  • max_tokens
  • presence_penalty
  • reasoning
  • repetition_penalty
  • seed
  • stop
  • temperature
  • top_k
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model deepseek/deepseek-r1-distill-llama-70b.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-r1-distill-llama-70b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="deepseek/deepseek-r1-distill-llama-70b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "deepseek/deepseek-r1-distill-llama-70b",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does R1 Distill Llama 70B cost via API?
Through OpenKey, R1 Distill Llama 70B costs $0.824 per 1M input tokens and $0.824 per 1M output tokens. That is the provider price ($0.800 / $0.800) plus a flat 3% fee — nothing else.
What is R1 Distill Llama 70B's context window?
R1 Distill Llama 70B accepts up to 128K tokens of context and returns up to 8K tokens per request.
Is R1 Distill Llama 70B OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "deepseek/deepseek-r1-distill-llama-70b" using any OpenAI SDK — only the base URL and API key change.
What inputs does R1 Distill Llama 70B support?
R1 Distill Llama 70B accepts text input and produces text output. Its knowledge cutoff is Jul 31, 2024.

More from DeepSeek

All DeepSeek models →