R1 Distill Llama 70B (free) Check detailed information and pricing for AI models

Context Length 8,192 tokens, deepseek from provided

8,192
Context Tokens
Free
Prompt Price
Free
Output Price
7/16
Feature Support

Model Overview

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.

Basic Information

Developer
deepseek
Model Series
Llama3
Release Date
2025-01-23
Context Length
8,192 tokens
Max Completion Tokens
4,096 tokens
Variant
free

Pricing Information

This model is free to use

Supported Features

Supported (7)

Top K
Frequency Penalty
Presence Penalty
Repetition Penalty
Min P
Logit Bias
Reasoning

Unsupported (9)

Image Input
Seed
Response Format
Tool Usage
Logprobs
Top Logprobs
Structured Outputs
Web Search Options
Top A

Other Variants

Actual Usage Statistics

#152
Out of 353 total models
1.6B
Total Tokens Last 30 Days
54.01M
Daily Average Usage
29%
Weekly Usage Change

Usage Trend for the Last 30 Days

Models by Same Author (deepseek)

DeepSeek V3.1
163,840 tokens
$0.20 / $0.80
DeepSeek V3.1 (free)
64,000 tokens
Free
DeepSeek V3.1 (thinking)
131,072 tokens
$0.55 / $2.19
DeepSeek V3.1 Base
163,840 tokens
$0.20 / $0.80
R1 Distill Qwen 7B
131,072 tokens
$0.00 / $0.00