R1 Distill Llama 70B

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 multiple benchmarks, including: - AIME 2024 pass@1: 70.0 - MATH-500 pass@1: 94.5 - CodeForces Rating: 1633 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

ChatDeepSeek8k tokens$0.872 / $0.872 · 1M

deepseek/deepseek-r1-distill-llama-70b

Context
8k tokens
Completion cap
8,192
Tools
No
JSON
No
Released
2025-01-23

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-r1-distill-llama-70b",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is R1 Distill Llama 70B?
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 multiple benchmarks, including: - AIME 2024 pass@1: 70.0 - MATH-500 pass@1: 94.5 - CodeForces Rating: 1633 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models. R1 Distill Llama 70B runs on the Geek Hub API (OpenAI-compatible). Model id: deepseek/deepseek-r1-distill-llama-70b.
Is R1 Distill Llama 70B free?
No. Input is $0.872 per 1M tokens and output is $0.872 per 1M tokens on Geek Hub (markup included).
What is the context length of R1 Distill Llama 70B?
R1 Distill Llama 70B has a 8k tokens context window. It supports up to 8,192 completion tokens.
Does R1 Distill Llama 70B support tool calling and structured outputs?
R1 Distill Llama 70B does not advertise tool calling on this endpoint. Structured outputs are not listed for this endpoint.
When was R1 Distill Llama 70B released?
R1 Distill Llama 70B was released on 2025-01-23.

More models from DeepSeek