gemini-2.5-pro Performance Analytics - Real-time Metrics, Token Usage & Cost Analysis

Back to Model Details
gemini

gemini-2.5-pro

gemini • Performance Analytics

Core Performance Metrics

Total Requests
215
43.3%
Error Rate
42.33%
54.9%
Total Input Tokens
2,382,810
48.0%
Total Output Tokens
168,171
15.5%

Access gemini-2.5-pro through LangDB AI Gateway

Recommended

Integrate with google's gemini-2.5-pro 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
11.94s
19.5%
TTFT
8.55s
14.8%
TPS (Tokens/Second)
993.8 TPS
22.2%
TPOT (Time/Output Token)
0.020ms

Performance Trends

Sep 4 - Sep 11, 2025

Request Volume
Daily API requests
215
Performance (TPS)
Tokens per second
993.81 tokens/s
Response Time
Average response latency (ms)
11939.00 ms
TTFT
Time to First Token (ms)
8549.10 ms

Token Analytics

Token usage distribution and efficiency metrics

Token Distribution
Input vs Output token usage
Input Tokens:2,382,810
Output Tokens:168,171
Total Tokens:2,550,981
Token Usage Timeline
Daily token consumption trends