R1 Distill Qwen 14B Check detailed information and pricing for AI models
Context Length 64,000 tokens, deepseek from provided
64,000
Context Tokens
$0.15
Prompt Price
$0.15
Output Price
8/16
Feature Support
Reasoning #12
Model Overview
DeepSeek R1 Distill Qwen 14B is a distilled large language model based on [Qwen 2.5 14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models. Other benchmark results include: - AIME 2024 pass@1: 69.7 - MATH-500 pass@1: 93.9 - CodeForces Rating: 1481 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.
Basic Information
Developer
deepseek
Model Series
Qwen
Release Date
2025-01-29
Context Length
64,000 tokens
Max Completion Tokens
32,000 tokens
Variant
standard
Pricing Information
Prompt Tokens
$0.15 / 1M tokens
Completion Tokens
$0.15 / 1M tokens
Data Policy
Supported Features
Supported (8)
Top K
Seed
Frequency Penalty
Presence Penalty
Repetition Penalty
Min P
Logit Bias
Reasoning
Unsupported (8)
Image Input
Response Format
Tool Usage
Logprobs
Top Logprobs
Structured Outputs
Web Search Options
Top A
Other Variants
Actual Usage Statistics
#215
Out of 345 total models
238.53M
Total Tokens Last 30 Days
7.95M
Daily Average Usage
61%
Weekly Usage Change