DeepSeek R1 Distill Qwen 14B
Reason Like o1-mini
Master Math Code Reasoning
Top Benchmarks
Outperforms o1-mini
DeepSeek R1 Distill Qwen 14B hits 93.9% MATH-500, 69.7% AIME 2024 pass@1.
128K Context
Handles Long Inputs
Supports 128k token context for complex chain-of-thought reasoning tasks.
Open Weights
API Ready Deploy
DeepSeek R1 Distill Qwen 14B API enables fast inference on dedicated GPUs.
Examples
See what DeepSeek R1 Distill Qwen 14B can create
Copy any prompt below and try it yourself in the playground.
Math Proof
“Solve this AIME-level problem step-by-step: Find the number of positive integers n such that n divides 2^n + 2. Explain each reasoning step clearly.”
Code Debug
“Write Python code to implement a binary search tree with insert and search functions. Include edge cases and optimize for O(log n) time.”
Logic Puzzle
“Three logicians A, B, C wear hats that are either red or blue. A sees two red hats, B sees one red one blue, C sees two blue. They deduce colors using logic.”
Algorithm Design
“Design an efficient algorithm to find the longest increasing subsequence in an array of integers. Provide pseudocode, time complexity, and example.”
For Developers
A few lines of code.
Reasoning LLM. One Call.
ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.
- Serverless: scales to zero, scales to millions
- Pay per token, no minimums
- Python and JavaScript SDKs, plus REST API
import requestsresponse = requests.post("https://modelslab.com/api/v7/llm/chat/completions",json={"key": "YOUR_API_KEY","prompt": "","model_id": ""})print(response.json())
Ready to create?
Start generating with DeepSeek R1 Distill Qwen 14B on ModelsLab.