AI usage
Requests, tokens, cost and latency across your models
Requests
85.1K
Tokens
43M
Spend
$152
p95 latency
1.32 s
Requests
638.4K
Tokens
326M
Spend
$1,144
p95 latency
1.42 s
Requests
2.7M
Tokens
1.37B
Spend
$4,816
p95 latency
1.42 s
Tokens by model
Millions, the last 24 hours, by hour
Tokens by model
Millions, the last 7 days, by day
Tokens by model
Millions, the last 30 days, by day
Spend by feature
$152, the last 24 hours
Spend by feature
$1,144, the last 7 days
Spend by feature
$4,816, the last 30 days
Endpoints
85.1K requests, the last 24 hours
| Endpoint | Model | p95 | Errors | |
|---|---|---|---|---|
/v1/chat |
Large | 36,920 | 1.86 s | 0.4% |
/v1/search |
Medium | 25,009 | 0.92 s | 0.2% |
/v1/summarize |
Medium | 12,249 | 1.31 s | 0.6% |
/v1/classify |
Small | 8,506 | 0.38 s | 0.1% |
/v1/images |
Large | 2,381 | 6.2 s | 1.8% |
Endpoints
638.4K requests, the last 7 days
| Endpoint | Model | p95 | Errors | |
|---|---|---|---|---|
/v1/chat |
Large | 277,085 | 1.86 s | 0.4% |
/v1/search |
Medium | 187,701 | 0.92 s | 0.2% |
/v1/summarize |
Medium | 91,935 | 1.31 s | 0.6% |
/v1/classify |
Small | 63,844 | 0.38 s | 0.1% |
/v1/images |
Large | 17,876 | 6.2 s | 1.8% |
Endpoints
2.7M requests, the last 30 days
| Endpoint | Model | p95 | Errors | |
|---|---|---|---|---|
/v1/chat |
Large | 1,165,938 | 1.86 s | 0.4% |
/v1/search |
Medium | 789,827 | 0.92 s | 0.2% |
/v1/summarize |
Medium | 386,854 | 1.31 s | 0.6% |
/v1/classify |
Small | 268,648 | 0.38 s | 0.1% |
/v1/images |
Large | 75,221 | 6.2 s | 1.8% |
Monthly budget
October, $6,000 limit
Forecast$5,070
Left$1,512
Latency
p50 and p95 in seconds, the last 24 hours, by hour
Latency
p50 and p95 in seconds, the last 7 days, by day
Latency
p50 and p95 in seconds, the last 30 days, by day
Top users
By tokens this month
-
ML12.0MtokensMaya LindqvistProduct Designer
-
MC9.2MtokensMei ChenProduct Manager
-
NF7.4MtokensNoah FischerBackend Engineer
-
FW5.2MtokensFelix WagnerData Engineer
-
AN4.6MtokensArjun NairMachine Learning Engineer