llama-3.1-8b-instruct

deepinfra • Performance Analytics

Core Performance Metrics

Total Requests

110

214.3%

Error Rate

0.00%

0.0%

Total Input Tokens

43,523

126.8%

Total Output Tokens

3,697

412.8%

Access llama-3.1-8b-instruct through LangDB AI Gateway

Recommended

Integrate with meta's llama-3.1-8b-instruct 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

0.78s

25.9%

TTFT

0.78s

25.8%

TPS (Tokens/Second)

551.0 TPS

1.8%

TPOT (Time/Output Token)

0.020ms

80.0%

Performance Analytics for llama-3.1-8b-instruct

Usage Statistics (Last 2 Days):

Total Requests: 110 API calls
Average TPS: 550.97 tokens per second
Average Response Time: 779.10ms
Average Time to First Token: 779.10ms
Total Cost: $0.00
Average Request Cost: $0.0000

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
11/12/2025	108	553.71	788.30ms	788.30ms	$0.00
11/15/2025	2	142.02	285.20ms	285.20ms	$0.00

Performance Summary:

Model: llama-3.1-8b-instruct by deepinfra

Monitoring Period: 11/11/2025 to 11/18/2025

Average Daily Requests: 55

Peak Daily Requests: 108

Performance Trends

Nov 11 - Nov 18, 2025

Request Volume

Daily API requests

110

Performance (TPS)

Tokens per second

550.97 tokens/s

Response Time

Average response latency (ms)

779.10 ms

TTFT

Time to First Token (ms)

779.10 ms

Token Analytics

Token usage distribution and efficiency metrics

Token Distribution

Input vs Output token usage

Input Tokens:43,523

Output Tokens:3,697

Total Tokens:47,220

Token Usage Timeline