kimi-k2-instruct

fireworksai • Performance Analytics

Core Performance Metrics

Total Requests

66.7%

Error Rate

0.00%

0.0%

Total Input Tokens

46,440

57.4%

Total Output Tokens

359

91.7%

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

3.68s

63.6%

TTFT

1.36s

14.9%

TPS (Tokens/Second)

4236.5 TPS

240.6%

TPOT (Time/Output Token)

0.030ms

70.0%

Performance Analytics for kimi-k2-instruct

Usage Statistics (Last 1 Days):

Total Requests: 3 API calls
Average TPS: 4236.50 tokens per second
Average Response Time: 3682.20ms
Average Time to First Token: 1356.20ms
Total Cost: $0.03
Average Request Cost: $0.0115

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
11/11/2025	3	4236.50	3682.20ms	1356.20ms	$0.03

Performance Summary:

Model: kimi-k2-instruct by fireworksai

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

Average Daily Requests: 3

Peak Daily Requests: 3

Performance Trends

Nov 11 - Nov 18, 2025

Request Volume

Daily API requests

Performance (TPS)

Tokens per second

4236.50 tokens/s

Response Time

Average response latency (ms)

3682.20 ms

TTFT

Time to First Token (ms)

1356.20 ms

Token Analytics

Token usage distribution and efficiency metrics

Token Distribution

Input vs Output token usage

Input Tokens:46,440

Output Tokens:359

Total Tokens:46,799

Token Usage Timeline