DeepSeek: R1 Distill Llama 70B
OpenAI • text • function-calling • json-mode
Provider ID
deepseek/deepseek-r1-distill-llama-70bDeepSeek 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.
Quick Summary
Best For:
High-volume, low-latency tasks where cost efficiency is paramount
Pricing:
$0.00/1M input tokens, $0.00/1M output tokens
Context Window:
131,072 tokens
Key Differentiator:
Cost-optimized for high-volume usage
Specifications
Context Window
131,072 tokens
Max Output Tokens
131,072 tokens
Streaming
Yes
JSON Mode
Yes
Vision
No
Tier
Affordable
Capabilities
text
function-calling
json-mode
Tags
affordable