llama-4-maverick Performance Analytics - Real-time Metrics, Token Usage & Cost Analysis

Back to Model Details
deepinfra

llama-4-maverick

deepinfra • Performance Analytics

Core Performance Metrics

Total Requests
2
100.0%
Error Rate
0.00%
0.0%
Total Input Tokens
95
Total Output Tokens
314

Access llama-4-maverick through LangDB AI Gateway

Recommended

Integrate with meta's llama-4-maverick 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
4.12s
100.0%
TTFT
0.54s
TPS (Tokens/Second)
49.6 TPS
100.0%
TPOT (Time/Output Token)
0.030ms

Performance Trends

Sep 22 - Sep 29, 2025

Request Volume
Daily API requests
2
Performance (TPS)
Tokens per second
49.63 tokens/s
Response Time
Average response latency (ms)
4120.80 ms
TTFT
Time to First Token (ms)
542.10 ms

Token Analytics

Token usage distribution and efficiency metrics

Token Distribution
Input vs Output token usage
Input Tokens:95
Output Tokens:314
Total Tokens:409
Token Usage Timeline
Daily token consumption trends