AI Analytics
A clearer view of your AI usage, performance, and spend.
Your AI workspace, at a glance
Sample data4 models in view · 99.7% successful requests · Period ending Oct 9, 2026
Total requests
171.8K
Tokens processed
61M
Total AI spend
$992.00
Average latency
0.79s
AI usage over time
Request and token volume over the last 30 days
Spend by model
Compare the cost of each AI model
Daily throughput
5.7K
requests per day
Cached tokens
7.3M
12% of processed tokens
Estimated cache savings
$119.04
at the average token rate
Failed requests
460
0.27% of total requests
Response time trends
Sample average and tail latency
Request activity
Requests grouped by weekday and hour over 30 days
AI spend budget
Manage your sample spending target
Spent
$992.00
Remaining
$8.00
Target adjusted to $1,000.00 for 30 days.
Token breakdown
Understand where your tokens go
61M
total processed tokens
Recent AI workloads
Sample runs from October 9, 2026
Weekly research summary
Atlas Pro · Oct 9, 14:32
12.5K tokens
1.4s
Support reply generation
Atlas Mini · Oct 9, 14:28
3.2K tokens
0.4s
Product image classification
Vision One · Oct 9, 14:21
8.2K tokens
3.1s
Knowledge base indexing
Embed v2 · Oct 9, 14:18
28.6K tokens
0.2s
Quarterly forecast review
Atlas Pro · Oct 9, 14:12
18.9K tokens
1.6s
Workspace insights
Based on the selected sampleUsage is growing
Request volume is up 18.5% compared with the previous period. Track capacity as your AI workflows scale.
171,800 requests processed
Keep an eye on cost
Your average cost is $5.77 per 1,000 requests. Route simple tasks to smaller models to keep spend predictable.
$33.07 average daily spend
Quality stays consistent
99.7% of requests completed successfully. Vision One has elevated latency; review image sizes and request complexity.
0.79s weighted average response
Model performance
Compare usage, reliability, and cost across your AI models
| Model | Requests | Tokens | Avg. latency | Success rate | Cost | Status | Details |
|---|---|---|---|---|---|---|---|
Atlas Pro Reasoning & analysis | 48.3K | 18.6M | 1.24s | 99.8% | $486.20 | Healthy | |
Atlas Mini Fast text generation | 72.5K | 24.2M | 0.42s | 99.9% | $168.40 | Healthy | |
Vision One Image understanding | 18.4K | 9.8M | 2.18s | 98.6% | $294.60 | Elevated latency | |
Embed v2 Search & retrieval | 32.6K | 8.4M | 0.18s | 99.9% | $42.80 | Healthy |