Monitoring

Real-time token usage, API costs, rate limits & agent utilization

Live · refreshes every 2.5s· Updated just now

Total Tokens

237,300

API Cost (session)

$3.19

Active Sessions

4 / 6

Throttled

1

Avg Utilization

52%

Token Usage

per session

Prompt

185.7k

Completion

51.6k

Total

237.3k

activethrottledidleerror

API Cost

this session
gpt-4o
$2.480
gpt-4-turbo
$0.620
gpt-3.5-turbo
$0.090

Session Total

$3.190

Projected / day

$76.56

Rate Limits

1 at risk

FullStack

4o

18 / 60 rpm30%
active

DataSci

4-turbo

12 / 60 rpm20%
active

AIEng

4o

58 / 60 rpm97%
throttled

PyDev

3.5-turbo

8 / 90 rpm9%
active

RevTest

4o

0 / 60 rpm0%
idle

DocGen

3.5-turbo

0 / 90 rpm0%
error
<70% safe 70–89% warn ≥90% critical

Agent Utilization

Capacity used per session

97%

AIEng-04

4o

throttled
87%

FullStack-01

4o

active
72%

DataSci-02

4-turbo

active
44%

PyDev-01

3.5-turbo

active
12%

RevTest-02

4o

idle
0%

DocGen-03

3.5-turbo

error

Session Breakdown

6 sessions
ModelStatusPromptCompletionLast Active
AIEng-04
gpt-4othrottled93,40072,10021,300$1.4005897%3s ago
FullStack-01
gpt-4oactive60,60048,20012,400$0.9101887%just now
DataSci-02
gpt-4-turboactive41,30031,5009,800$0.6201272%12s ago
PyDev-01
gpt-3.5-turboactive24,10018,9005,200$0.070844%28s ago
RevTest-02
gpt-4oidle11,5009,4002,100$0.170012%4m ago
DocGen-03
gpt-3.5-turboerror6,4005,600800$0.02000%11m ago