R1 Distill Llama 70B Check detailed information and pricing for AI models
Context Length 131,072 tokens, deepseek from provided
131,072
Context Tokens
$0.10
Prompt Price
$0.40
Output Price
8/16
Feature Support
science #15
Reasoning #11
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
131,072 tokens
Max Completion Tokens
16,384 tokens
Variant
standard
Pricing Information
Prompt Tokens
$0.10 / 1M tokens
Completion Tokens
$0.40 / 1M tokens
Data Policy
Supported Features
Supported (8)
Top K
Seed
Frequency Penalty
Presence Penalty
Repetition Penalty
Response Format
Min P
Reasoning
Unsupported (8)
Image Input
Logit Bias
Tool Usage
Logprobs
Top Logprobs
Structured Outputs
Web Search Options
Top A
Other Variants
Actual Usage Statistics
#51
Out of 346 total models
17.3B
Total Tokens Last 30 Days
575.52M
Daily Average Usage
61%
Weekly Usage Change