deepseek-r1-0528-qwen3-8b

parasail • Performance Analytics

Core Performance Metrics

Total Requests

225.0%

Error Rate

0.00%

0.0%

Total Input Tokens

124,324

133.2%

Total Output Tokens

12,069

188.9%

Access deepseek-r1-0528-qwen3-8b through LangDB AI Gateway

Recommended

Integrate with deepseek's deepseek-r1-0528-qwen3-8b 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

30.68s

17.2%

TTFT

2.00s

89.0%

TPS (Tokens/Second)

342.0 TPS

11.9%

TPOT (Time/Output Token)

0.030ms

Performance Analytics for deepseek-r1-0528-qwen3-8b

Usage Statistics (Last 2 Days):

Total Requests: 13 API calls
Average TPS: 342.03 tokens per second
Average Response Time: 30675.30ms
Average Time to First Token: 1999.20ms
Total Cost: $0.01
Average Request Cost: $0.0007

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
9/4/2025	12	369.07	30016.60ms	2092.10ms	$0.01
9/5/2025	1	89.55	38580.00ms	884.60ms	$0.00

Performance Summary:

Model: deepseek-r1-0528-qwen3-8b by parasail

Monitoring Period: 9/4/2025 to 9/11/2025

Average Daily Requests: 7

Peak Daily Requests: 12

Performance Trends

Sep 4 - Sep 11, 2025

Request Volume

Daily API requests

Performance (TPS)

Tokens per second

342.03 tokens/s

Response Time

Average response latency (ms)

30675.30 ms

TTFT

Time to First Token (ms)

1999.20 ms

Token Analytics

Token usage distribution and efficiency metrics

Token Distribution

Input vs Output token usage

Input Tokens:124,324

Output Tokens:12,069

Total Tokens:136,393

Token Usage Timeline