DeepSeek-R1-Distill-Qwen-32B Performance Analytics - Real-time Metrics, Token Usage & Cost Analysis

Back to Model Details
deepinfra

DeepSeek-R1-Distill-Qwen-32B

deepinfra • Performance Analytics

Core Performance Metrics

Total Requests
5
100.0%
Error Rate
0.00%
0.0%
Total Input Tokens
68,886
Total Output Tokens
2,291

Access DeepSeek-R1-Distill-Qwen-32B through LangDB AI Gateway

Recommended

Integrate with deepseek's DeepSeek-R1-Distill-Qwen-32B and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API
Cost Optimization
Enterprise Security
Get Started Now

Free tier available • No credit card required

Instant Setup
99.9% Uptime
10,000+Monthly Requests

Performance Percentiles

Response Time
10.96s
100.0%
TTFT
9.61s
TPS (Tokens/Second)
1298.5 TPS
100.0%
TPOT (Time/Output Token)
0.020ms

Performance Trends

Sep 16 - Sep 23, 2025

Request Volume
Daily API requests
5
Performance (TPS)
Tokens per second
1298.45 tokens/s
Response Time
Average response latency (ms)
10963.40 ms
TTFT
Time to First Token (ms)
9614.80 ms

Token Analytics

Token usage distribution and efficiency metrics

Token Distribution
Input vs Output token usage
Input Tokens:68,886
Output Tokens:2,291
Total Tokens:71,177
Token Usage Timeline
Daily token consumption trends