Cursor
Cursor's model picker only shows what Cursor itself has integrated and priced. Override its OpenAI base URL to point at Tempr Gateway instead, and the AI panel can run any model on your own gateway allowlist — including ones Cursor doesn't offer at all — billed through your own BYOK keys instead of Cursor's managed plans.
-
Create a virtual key
In the Portal, create a Gateway virtual key. Keys are prefixed
tvk_and shown once at creation. -
Add a provider key
Gateway is BYOK: add a key for at least one provider from the supported list.
-
Configure Cursor
Open Settings → Cursor Settings → Models. Enable Override OpenAI Base URL and set it to
https://api.temprhq.io/v1. Click Add OpenAI API Key and paste your virtual key.
Tab autocomplete and inline edit (Cmd/Ctrl + K) stay on Cursor's own backend regardless of this setting — it's a Cursor architecture detail, not a Tempr limitation. Only the AI panel (chat and agent mode) routes through the custom base URL.
Model ids
Use the fully-qualified provider/model form (e.g. anthropic/claude-sonnet-4-5, openai/gpt-5) — the same ids GET /v1/models returns.
What's next
- Authentication & virtual keys — scoping keys with model allowlists, budgets, and rate limits.
- Models, limits & logs — request logs and analytics for everything you send through the gateway.