Budgets and tiers

Foxl Code meters managed model tokens and Remote compute against your account credits. This includes browser chat, coding agents, scheduled work, and background reviews. Desktop local model usage stays on your own provider or subscription.

Credits and actual usage

One credit has a displayed value of $0.04. Model charges use $0.036 of provider cost per credit; the difference is Foxl's margin. Compute is recorded separately in the same wallet.

Before each model request, Relay checks the available balance and reserves credits. It can lower the requested output limit to what the balance can afford, or refuse the request when the balance is insufficient. After the response, it charges the reported input, output, cache-read, and cache-write tokens and releases the reservation. Reasoning tokens count as output usage.

Usage / Account shows your balance, model usage, compute, and ledger even when plan checkout is unavailable. A budget is an allowance, not an upfront charge.

Per-task budgets

Each task receives a model-and-compute estimate and a task budget. Settings > Code > Defaults & budget > Max spend per task supplies the default budget allowance (initially $500); the task estimate can raise that allowance when it is larger. Review the assigned budget before starting expensive or autonomous work.

Relay stops admitting further model calls when the task's recorded spend and reservations reach its budget. This is a soft task ceiling: a response already in flight can exceed the task estimate, concurrent calls can finish together, and compute is settled after execution. The per-request credit reservation separately limits model output to what the wallet can fund. Do not treat the task budget as a guarantee of zero overshoot.

The time limit in Settings > Code > Container also bounds a run: 30 minutes by default, up to 8 hours. At shutdown the harness attempts to commit and push the work it has.

Admission and plan limits

A managed task needs:

• An enabled Code account and an available managed runtime.
• A supported backend and a compatible model from the Code catalog.
• Repository access through the GitHub App.
• A positive credit balance and an available task slot. Free accounts can run up to five tasks concurrently; model calls also have request-concurrency limits.

The managed catalog is available to credit-bearing Free accounts as well as paid tiers. It does not require a personal model-provider credential. Credit checks and task budgets apply regardless of whether paid plans are advertised.

Pro/Ultra checkout and top-up sales are a separate rollout. Restoring managed inference does not enable them. If checkout is unavailable, use the balance and next refresh date shown in your account; no purchase option is implied by the model picker.

Model rates used by Relay

Base provider rates, in USD per million tokens, before conversion to credits:

Cache writes, where supported, are charged separately. GPT-6 Astra requests above 272,000 total input tokens, including cached input, use twice the base input/cache rates and 1.5 times the output rate for the entire request. Relay applies that band to reservations and settlement.

Remote compute charges depend on active CPU time and memory duration. A connected machine uses your own infrastructure instead; managed model calls from it still use Code credits. Fully local Desktop execution uses neither Remote compute nor Foxl model credits.