Model access
Foxl Code uses managed Relay credits; Foxl Desktop keeps your own keys and subscriptions
Model access
Foxl Code and Foxl Desktop have two distinct paths for model access.
| Where you run | Who supplies model access | Who bills model usage |
|---|---|---|
| code.foxl.ai orchestrator and coding agents | Foxl-managed Amazon Bedrock through Relay | Foxl account credits |
| Remote tasks opened from any Foxl app | The same managed Code service | Foxl account credits |
| Foxl Desktop local orchestrator and This computer agents | Your provider key, local model, or supported subscription (BYOK/BYOA) | Your provider or subscription; no Foxl model charge |
| A connected machine executing a managed Code task | Foxl Relay for models; your machine for compute | Foxl credits for models; your infrastructure bill for that machine |
A Desktop provider login does not become model access for code.foxl.ai. The SaaS model and agent pickers use the managed catalog, and cloud tasks do not consume personal credentials previously synced to Code.
The website works with Desktop closed or uninstalled. It does not pair with Desktop, discover local providers, or connect to a local terminal. Older local-machine defaults and saved Desktop connection settings cannot send a website task to your computer; use Foxl Desktop for local execution.
Managed orchestrator models
Choose the model beside the chat composer. The managed catalog contains 19 models:
| Family | Models |
|---|---|
| Claude | Opus 5, Fable 5.1, Fable 5, Opus 4.8, Opus 4.7, Opus 4.6, Sonnet 5, Sonnet 4.6, Haiku 4.5 |
| OpenAI | GPT-6 Astra, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, GPT-5.5, GPT-5.4 |
| Z.AI | GLM 5 |
| Moonshot | Kimi K2.5 |
| xAI | Grok 4.6 |
| Gemma 4 31B |
Older versions can be hidden by your model-picker preferences while remaining available to saved selections. Models that support reasoning expose their supported thinking and effort controls.
Gemma 4 31B is chat-only in Code. It can answer and transform text, but cannot inspect repositories or launch coding agents. Choose a tool-capable model for orchestration.
The managed catalog is available to enabled accounts with credits, including Free accounts. Balance, request-concurrency, task, and repository-access limits still apply. A listed model is not a promise of unlimited usage.
Managed coding agents
The coding CLI determines which model family it can use:
| Agent | Managed models |
|---|---|
| Claude Code | Claude |
| Codex | GPT |
| Hermes | Claude |
| OpenCode | Claude |
Choose these under Settings > Code > Coding agent or in the task picker. No personal model credential is required. Backend availability also depends on which runtimes are provisioned for the environment.
Kiro and Cursor use their vendors' authentication paths, so they are not offered as managed cloud agents. They remain available for supported local Desktop use with your own login.
What uses credits
Cloud chat, coding-agent model turns, and background orchestration or reviews use the same Relay credit meter. Remote compute is also metered. Select a model and set task budgets before enabling autonomous or scheduled work.
Open Usage / Account in Code to see the balance, token usage, compute charges, and ledger. These remain visible even when purchasing plans or top-ups is unavailable. Credit accounting and checkout availability are separate.
If managed inference is temporarily unavailable, Code refuses new model work. It does not switch to your Desktop keys or subscriptions. Desktop local use remains available through its configured providers.