gemini-2.5-flash

gemini • Performance Analytics

Core Performance Metrics

Total Requests

237

1723.1%

Error Rate

16.88%

9.8%

Total Input Tokens

9,827,311

4636.5%

Total Output Tokens

244,334

3257.6%

Access gemini-2.5-flash through LangDB AI Gateway

Recommended

Integrate with google's gemini-2.5-flash 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

9.39s

100.0%

TTFT

2.68s

56.8%

TPS (Tokens/Second)

4525.0 TPS

28.6%

TPOT (Time/Output Token)

0.010ms

Performance Analytics for gemini-2.5-flash

Usage Statistics (Last 5 Days):

Total Requests: 237 API calls
Average TPS: 4524.97 tokens per second
Average Response Time: 9391.50ms
Average Time to First Token: 2680.80ms
Total Cost: $1.94
Average Request Cost: $0.0082

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
10/5/2025	17	10241.24	7222.30ms	1430.10ms	$0.23
10/6/2025	84	6736.91	9622.50ms	2780.80ms	$1.03
10/7/2025	46	9420.96	5629.20ms	1148.80ms	$0.45
10/8/2025	51	674.45	16070.00ms	4233.50ms	$0.16
10/9/2025	39	1741.69	5543.80ms	2787.60ms	$0.08

Performance Summary:

Model: gemini-2.5-flash by gemini

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

Average Daily Requests: 47

Peak Daily Requests: 84

Performance Trends

Oct 2 - Oct 9, 2025

Request Volume

Daily API requests

237

Performance (TPS)

Tokens per second

4524.97 tokens/s

Response Time

Average response latency (ms)

9391.50 ms

TTFT

Time to First Token (ms)

2680.80 ms

Token Analytics

Token usage distribution and efficiency metrics

Token Distribution

Input vs Output token usage

Input Tokens:9,827,311

Output Tokens:244,334

Total Tokens:10,071,645

Token Usage Timeline