Pro tokens cover the listed models, so a team sends its first real request without adding a provider key.
Start without registering a provider key
The original Pro announcement introduced access to the listed managed models through Stimulir. Managed inference uses the routes and credits available to your workspace, so you can make a request before adding a separate provider credential.
Choose an available model
Select your workspace and project, then inspect the model catalogue before sending a request. Use a returned model identifier with the inference gateway; do not assume that a model shown in an old announcement is still enabled for your account.
Check usage and plan limits
Review the current plan, remaining credits and recorded usage in the Console. Availability and billing depend on your workspace configuration. The usage and billing reference explains the measurements to inspect. This historical note is not a current price list or a promise of unlimited usage.
Bring a provider key when appropriate
You can also register your own provider credential through BYOK. Keep provider credentials and Stimulir application keys separate: provider credentials configure the upstream service, while your application authenticates to Stimulir with its own key.
About this entry
This expands the original 15 September 2026 announcement. Its original deployment record was not retained. Check the current Console plan and model catalogue for the terms and models available to your workspace.