gemini-2.5-flash-preview

gemini • Performance Analytics

Core Performance Metrics

Total Requests

220

71.9%

Error Rate

15.45%

67.6%

Total Input Tokens

3,308,610

228.2%

Total Output Tokens

208,183

206.3%

Access gemini-2.5-flash-preview through LangDB AI Gateway

Recommended

Integrate with google's gemini-2.5-flash-preview 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

8.89s

39.2%

TTFT

5.06s

56.5%

TPS (Tokens/Second)

1798.8 TPS

36.6%

TPOT (Time/Output Token)

0.010ms

Performance Analytics for gemini-2.5-flash-preview

Usage Statistics (Last 4 Days):

Total Requests: 220 API calls
Average TPS: 1798.85 tokens per second
Average Response Time: 8886.50ms
Average Time to First Token: 5055.30ms
Total Cost: $0.75
Average Request Cost: $0.0034

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
10/4/2025	87	2294.76	6767.50ms	4148.20ms	$0.27
10/5/2025	31	1398.90	13035.30ms	6921.10ms	$0.13
10/6/2025	68	1919.95	10336.80ms	5228.10ms	$0.29
10/7/2025	34	967.69	7625.20ms	5329.20ms	$0.06

Performance Summary:

Model: gemini-2.5-flash-preview by gemini

Monitoring Period: 10/2/2025 to 10/9/2025

Average Daily Requests: 55

Peak Daily Requests: 87

Performance Trends

Oct 2 - Oct 9, 2025

Request Volume

Daily API requests

220

Performance (TPS)

Tokens per second

1798.85 tokens/s

Response Time

Average response latency (ms)

8886.50 ms

TTFT

Time to First Token (ms)

5055.30 ms

Token Analytics

Token usage distribution and efficiency metrics

Token Distribution

Input vs Output token usage

Input Tokens:3,308,610

Output Tokens:208,183

Total Tokens:3,516,793

Token Usage Timeline