Usage and costs
Inspect local usage
Inspect usage recorded by fx on this machine:
fx usageChoose a period or return structured output:
fx usage --period 24h --jsonValid periods are 24h, 7d, and 30d. Reports include requests, tokens, recorded spend, and usage by model. They also indicate when tracking covers only part of the selected period or totals may be incomplete.
Inside the shell, /usage opens the dashboard. /cost is an alias.
Usage is local
fx usage only includes requests recorded by fx on this machine. It does not query team-wide AI Gateway usage.
Every model request from fx goes through AI Gateway, whether you sign in with Vercel or use an AI Gateway API key. View usage for the active credential in your team's AI Gateway dashboard.
Additional model requests
Two features use a fixed helper model and create an additional AI Gateway request. This is the canonical list; other pages link here rather than repeat the model IDs.
| Feature | Helper model | When it runs |
|---|---|---|
| Automatic permission review | openai/gpt-5.4 | An unresolved sensitive tool call in auto mode. |
| Vision fallback | google/gemini-2.5-flash | Attached images cannot be sent to the selected model natively. |
These requests contribute to usage and cost. Neither helper model is configurable, and changing the selected model does not change either one.
Web search uses an AI Gateway provider tool rather than a fixed helper model. Provider search calls can add cost to the generation that invokes them, and that cost is included in the recorded generation total.
Check your AI Gateway balance
To query the balance for the active AI Gateway credential:
fx creditsfx balance is an alias. Inside the shell, use /credits or /balance.