DeepSeek: R1 Distill Qwen 32B

Text input Text output
Author's Description

DeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](https://huggingface.co/Qwen/Qwen2.5-32B), 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.\n\nOther benchmark results include:\n\n- AIME 2024 pass@1: 72.6\n- MATH-500 pass@1: 94.3\n- CodeForces Rating: 1691\n\nThe model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

Key Specifications
Cost
$$$
Context
131K
Parameters
32B
Released
Jan 29, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Include Reasoning Response Format Stop Max Tokens Top P Frequency Penalty Reasoning Min P Seed Temperature Presence Penalty
Features

This model supports the following features:

Reasoning Response Format
Performance Summary

DeepSeek R1 Distill Qwen 32B, a distilled model based on Qwen 2.5 32B and fine-tuned with DeepSeek R1 outputs, demonstrates a strong performance profile, particularly in reliability and certain cognitive tasks. The model exhibits exceptional reliability with a 99% success rate, indicating consistent and stable operation. However, its speed performance is a notable area for improvement, ranking in the 13th percentile, suggesting longer response times compared to many peers. In terms of cost, it offers generally competitive pricing, falling within the 60th percentile. Analyzing benchmark results, the model shows significant strengths in Coding (89th percentile accuracy) and Reasoning (85th percentile accuracy), achieving high scores in complex problem-solving and programming knowledge. Its Mathematics performance is also robust at the 80th percentile. General Knowledge is strong at 62nd percentile. A key weakness is observed in Hallucinations, where its 60.0% accuracy places it in the 11th percentile, indicating a tendency to generate information rather than acknowledge uncertainty. Instruction Following and Ethics benchmarks show moderate performance, at the 52nd and 36th percentiles respectively. Overall, DeepSeek R1 Distill Qwen 32B excels in tasks requiring logical deduction and structured problem-solving, while its speed and handling of uncertainty present opportunities for enhancement.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.27
Completion $0.27

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
DeepInfra
DeepInfra | deepseek/deepseek-r1-distill-qwen-32b 131K $0.27 / 1M tokens $0.27 / 1M tokens
Novita
Novita | deepseek/deepseek-r1-distill-qwen-32b 64K $0.27 / 1M tokens $0.27 / 1M tokens
GMICloud
GMICloud | deepseek/deepseek-r1-distill-qwen-32b 131K $0.27 / 1M tokens $0.27 / 1M tokens
Cloudflare
Cloudflare | deepseek/deepseek-r1-distill-qwen-32b 80K $0.5 / 1M tokens $4.88 / 1M tokens
Nineteen
Nineteen | deepseek/deepseek-r1-distill-qwen-32b 16K $0.27 / 1M tokens $0.27 / 1M tokens
NextBit
NextBit | deepseek/deepseek-r1-distill-qwen-32b 32K $0.29 / 1M tokens $0.29 / 1M tokens
Novita
Novita | deepseek/deepseek-r1-distill-qwen-32b 64K $0.3 / 1M tokens $0.3 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by deepseek