gpt-oss-120b

deepinfra • Performance Analytics

Core Performance Metrics

Total Requests

148

322.9%

Error Rate

0.00%

0.0%

Total Input Tokens

12,367

371.1%

Total Output Tokens

8,190

484.2%

Access gpt-oss-120b through LangDB AI Gateway

Recommended

Integrate with openai's gpt-oss-120b 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

3.30s

264.9%

TTFT

3.18s

253.3%

TPS (Tokens/Second)

42.1 TPS

66.9%

TPOT (Time/Output Token)

0.060ms

Performance Analytics for gpt-oss-120b

Usage Statistics (Last 7 Days):

Total Requests: 148 API calls
Average TPS: 42.13 tokens per second
Average Response Time: 3296.60ms
Average Time to First Token: 3179.40ms
Total Cost: $0.01
Average Request Cost: $0.0000

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
10/3/2025	19	142.53	806.10ms	806.10ms	$0.00
10/4/2025	7	155.52	730.30ms	730.30ms	$0.00
10/5/2025	1	177.63	636.20ms	636.20ms	$0.00
10/6/2025	49	24.69	4727.80ms	4727.80ms	$0.00
10/7/2025	66	35.89	3199.70ms	3199.70ms	$0.00
10/8/2025	5	173.02	4684.90ms	1215.00ms	$0.00
10/9/2025	1	202.64	562.60ms	562.60ms	$0.00

Performance Summary:

Model: gpt-oss-120b by deepinfra

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

Average Daily Requests: 21

Peak Daily Requests: 66

Performance Trends

Oct 2 - Oct 9, 2025

Request Volume

Daily API requests

148

Performance (TPS)

Tokens per second

42.13 tokens/s

Response Time

Average response latency (ms)

3296.60 ms

TTFT

Time to First Token (ms)

3179.40 ms

Token Analytics

Token usage distribution and efficiency metrics

Token Distribution

Input vs Output token usage

Input Tokens:12,367

Output Tokens:8,190

Total Tokens:20,557

Token Usage Timeline