Usage
Usage.
Hosted API usage from Inferoptimal's ledger. Inferoptimal cloud endpoints are metered by the minute on the Billing page. Endpoints in your own cloud are billed by that cloud and are not metered here.
Hosted API
Requests, 30 d
—
Input tokens, 30 d
—
Output tokens, 30 d
—
settled requests only
Spent, 30 d
—
at the published per-token prices
Spent, month to date
—
| Model | Requests | Input | Cached | Output | Spent |
|---|---|---|---|---|---|
| Loading… | |||||
Dedicated endpoints
billed by your cloud; Inferoptimal cloud hours are on the Billing page| Endpoint | Model · hardware | State | Requests | Tokens | Billed to | AWS list price |
|---|---|---|---|---|---|---|
| Loading… | ||||||
Requests travel from Cloudflare to the instance in your account and are not counted on the way. Use CloudWatch or your own gateway for request counts.