A Playground under each project: send a request from the console and read its receipt
Playground, next to Dispatch and Logs, sends a chat, Messages, Responses, embeddings or images request as one of the project's keys and shows the streamed answer with its receipt beside it: the model and provider that served it, every upstream call and the routes skipped, time to first token, tokens and the charge, with a link to the request in Logs. Only models and aliases the project's Directives allow are offered, so a denial is explained where the Directive lives.
Copy the call as curl, the OpenAI or Anthropic client, or the AI SDK, with the key left for you to fill in. Calls run through the same admission as the API and are billed to the team like any request; owners and admins can run them.
What you typed stays in your browser per project. The first request from the quickstart can now be made here before a line of code is written.
More in Quickstart.