# Request Fast mode

Use `/gentle:profiles` to save **Standard** or **Fast** per compatible model route. Select a row and press `t` (or click the tier) to switch it. Click **All Fast** in the table header or press `a` to set the orchestrator and every compatible agent route in the current profile to Fast; already-Fast routes stay Fast, and unsupported or inherited routes are unchanged. This edits the draft only: save and choose **Use in this session** to persist and apply it. The profile's session snapshot restores the selection when the session is resumed. **Make default** applies the choice now and supplies the orchestrator tier for new sessions; already-running sessions keep their frozen startup default unless they apply a profile themselves. Child and direct routes use their own configured tiers.

After installing or updating the extension, run `/reload` to load it. The bottom bar shows the orchestrator's configured **Standard** or **Fast** next to its effort. It reads the named profile's saved configuration, not an older session snapshot or a server response. Tier status is not listed in Integrations.

This is a configuration indicator, not confirmation of server processing, billing, or account eligibility. Save and choose **Use in this session** to apply changes to the current session; the indicator itself does not change request routing. Older profiles without a tier keep existing request behavior and clear a previous profile selection when applied. An explicit profile session snapshot restores its request tier on reload or resume.

## Availability and cost

OpenAI documents that Codex Fast uses **2.5x included subscription usage** or **2x purchased credits**. API use follows its own pricing, not those subscription multipliers. Check your account, plan, model availability, and current [Codex Fast documentation](https://developers.openai.com/codex/speed) and [API pricing](https://openai.com/api/pricing/) before use. Pi's local cost estimates may not reflect actual tier, subscription quota, or billed charges; consult OpenAI for authoritative usage and billing.

The selector applies only to `openai` / `openai-responses` (including native ChatGPT sign-in) and `openai-codex` / `openai-codex-responses` (legacy sign-in), for these model IDs: `gpt-5.6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-6-astra`, `gpt-6-sol`, `gpt-6-luna`, `gpt-6.1-sol`, and `gpt-6.1-terra`. This conservative list reflects the installed model catalog and OpenAI's documented Codex Fast family; it is not an entitlement check. Other providers, APIs, and models are untouched. A profile tier belongs only to its selected model and clears when you switch to a different model.

Fast sends `service_tier: priority`; Standard sends `service_tier: default`, clearing a previous Fast request on supported models. Other payload fields are preserved. The server may reject or handle a request differently; the extension does not retry or automatically fall back. No separate tier-observation integration is registered. Native response-tier accounting remains unchanged and may depend on the provider's response. Other extensions can also alter a request later in the chain.