Cost & model access
Managed Foxl Code credits and Desktop provider billing are separate model-access paths
Cost & model access
Foxl Code is a managed SaaS; Foxl Desktop keeps BYOK/BYOA. The model-access path determines how usage is billed, even when both products are opened from the same app.
| Path | Model access | Model bill |
|---|---|---|
| code.foxl.ai and Remote Code tasks | Foxl-managed Amazon Bedrock through Relay | Foxl account credits |
| Desktop local chat and coding agents | Your provider key, local model, or supported subscription | Your provider/subscription |
See Code model access for the managed catalog and AI Providers to connect your Desktop providers.
Desktop: bring your own access
Under Settings > Model & provider, connect a provider API key, use Ollama / vLLM / LM Studio, or sign in with a supported Claude, ChatGPT, or Gemini CLI account. Foxl does not add a model charge for these local paths. Your provider's usage limits, subscription terms, and any extra-usage charges still apply.
The desktop relay tunnel used to reach your computer from another device is separate from managed model inference. A request sent to your Desktop provider stays on that provider's billing path.
Code: managed credits
Cloud chat, coding-agent turns, scheduled orchestration, and reviews use Foxl Relay. Remote compute is metered too. No personal API key, subscription upload, or AWS account is required for managed models. A connected machine supplies its own compute while the models for its managed Code tasks still draw on credits.
One account wallet holds Foxl credits. 1 credit has a displayed value of $0.04 and covers $0.036 of model-provider cost. The meter reserves credits before a request, settles actual reported token usage afterward, and releases the hold. Other enabled metered services, such as Relay transcription, can use the same wallet. Desktop BYOK/BYOA model calls do not debit it.
See Budgets and tiers for the current model rates, long-context pricing, compute charges, and the limits of per-task budgets.
What increases model usage
- Longer conversation history is sent again as input on later turns.
- Reasoning consumes output tokens.
- Tool results and additional agent turns add model requests.
- Concurrent coding agents, scheduled work, and background reviews each use their own requests.
- Cache reads can reduce input cost; cache writes have their own rate where supported.
Credit refresh and the usage window
Free accounts receive 10 monthly credits on their signup day-of-month at midnight UTC. Monthly grants do not accumulate across periods. Welcome credits are separate: 200 for Google, Apple, or GitHub signup and 50 for magic-link signup, without an expiry. Existing paid-tier grants follow the billing renewal date.
The period shown in your account follows that grant or renewal date, not necessarily the first of the month. An anchor on a missing day in a shorter month uses that month's last day, then returns to the original day in the next month. Your account shows the next refresh date.
Workspace storage and Channels follow the account's billing anchor where those services are chargeable. Unpaid metered charges are recorded and retried when credits are available. Free plans are not charged for workspace storage or Channels.
Check your balance
Open Usage / Account in Code to inspect the balance, token breakdown, compute, and ledger. Usage remains visible independently of whether paid plans or top-ups are offered. The restoration of managed models does not itself enable checkout.
A positive balance allows a task to be considered for admission; each model request still needs enough available credits after existing reservations. Running out of credits stops new managed requests. A budget is not an advance debit: the ledger records usage as it is settled.
Troubleshooting
Managed inference is unavailable: Code cannot currently admit cloud model work. Retry when service is available; changing a Desktop provider does not enable SaaS inference. This is an availability/policy response, not a reason to sign out.
Insufficient credits: inspect your available balance and pending work. Existing requests can hold credits, and a large input can cost more than the remaining balance. Shorten the request or wait for the account's next available grant or enabled purchase option.
No Desktop provider connected: configure one under Settings > Model & provider. This message belongs to the local Desktop path. Cloud Code uses its managed catalog instead.