Last updated: 16/04/2025

GroqOfficial Docs

DeepSeek R1 Distill Llama 70B

deepseek-r1-distill-llama-70b

active

DeepSeek R1 Distill Llama 70B

DeepSeek R1 Distill Llama 70B is a large language model with a 128K token context window, available as a preview model on Groq's platform. It supports a wide range of capabilities, including text, image, video, audio, transcription, and text-to-speech, making it a versatile tool for various AI applications.

Supports a 131,072 token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications.

Additional Information

Notes

This model is categorized as a preview model by Groq, intended for evaluation purposes only and not recommended for production environments. It has a context length of 131,072 tokens and runs at approximately 275 tokens per second on Groq's platform. Input tokens are priced at $0.75 per million tokens, and output tokens at $0.99 per million tokens.

Capabilities

Text

Input Pricing

$0.00/ KTok

Context: 131,072 tokens

Output Pricing

$0.00/ KTok

Image

Input Pricing

6400 tokens/image

Text-to-Speech

Text-to-Speech Pricing

$0.05/1k characters

Embeddings

Embeddings Pricing

$0.90/1k tokens

Flatten your repo for AI in seconds

Flatten repos. Prompt faster. One click → one GPT-ready file

Free Online & Desktop