DeepSeek: R1 Distill Llama 70B

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

Created Jan 23, 2025131,072 context
$0.05/M input tokens$0.05/M output tokens

DeepSeek R1 Distill Llama 70B is a distilled large language model based on Llama-3.3-70B-Instruct, using outputs from 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.

Apps using R1 Distill Llama 70B

Top public apps this week using this model

1.
liteLLM
Open-source library to simplify LLM calls
11.3Btokens
2.
Roo Code
A whole dev team of AI agents in your editor
15.7Mtokens
3.
12.4Mtokens
4.
11.5Mtokens
5.
10.1Mtokens
6.
Cline
Autonomous coding agent right in your IDE
9.07Mtokens
7.
Kilo Code
AI coding agent for VS Code
7.75Mtokens
8.
New API
LLM gateway, fork of One API
5.38Mtokens
9.
SillyTavern
LLM frontend for power users
5.08Mtokens
10.
2.52Mtokens
11.
OpenRouter: Chatroom
Chat with multiple LLMs at once
1.64Mtokens
12.
Chub AI
GenAI for everyone
1.42Mtokens
13.
1.36Mtokens
14.
850Ktokens
15.
841Ktokens
16.
793Ktokens
17.
745Ktokens
18.
741Ktokens
19.
667Ktokens
20.
Open WebUI
Extensible, self-hosted AI interface
483Ktokens

More models from DeepSeek

    Apps Using DeepSeek: R1 Distill Llama 70B | OpenRouter