kimi-k2-instruct

fireworksai • Performance Analytics

Core Performance Metrics

Total Requests

77.5%

Error Rate

1.27%

353.6%

Total Input Tokens

609,347

86.6%

Total Output Tokens

17,708

82.3%

Access kimi-k2-instruct through LangDB AI Gateway

Recommended

Integrate with moonshotai's kimi-k2-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

4.59s

31.8%

TTFT

0.62s

6.4%

TPS (Tokens/Second)

1730.7 TPS

12.4%

TPOT (Time/Output Token)

0.020ms

Performance Analytics for kimi-k2-instruct

Usage Statistics (Last 3 Days):

Total Requests: 79 API calls
Average TPS: 1730.72 tokens per second
Average Response Time: 4586.20ms
Average Time to First Token: 618.00ms
Total Cost: $0.49
Average Request Cost: $0.0062

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
9/6/2025	11	1156.11	6487.90ms	727.30ms	$0.07
9/7/2025	16	2756.75	4549.00ms	795.90ms	$0.15
9/9/2025	52	1576.38	4195.30ms	540.20ms	$0.27

Performance Summary:

Model: kimi-k2-instruct by fireworksai

Monitoring Period: 9/4/2025 to 9/11/2025

Average Daily Requests: 26

Peak Daily Requests: 52

Performance Trends

Sep 4 - Sep 11, 2025

Request Volume

Daily API requests

Performance (TPS)

Tokens per second

1730.72 tokens/s

Response Time

Average response latency (ms)

4586.20 ms

TTFT

Time to First Token (ms)

618.00 ms

Token Analytics

Token usage distribution and efficiency metrics

Token Distribution

Input vs Output token usage

Input Tokens:609,347

Output Tokens:17,708

Total Tokens:627,055

Token Usage Timeline