Skip to content

Use the AI playground with an available model

Test managed text, embedding, audio, or image operations using the live model catalog.

Before you start

Select the account to pay for requests. The playground lists model availability and limits; implemented operations can remain disabled without certified capacity.

Steps

  1. Open AI playground in Developer tools.
  2. Choose an enabled model and inspect its operation, price, input limits, and maximum output settings.
  3. Enter a small test input and select a project where available.
  4. Review any cost estimate or reservation and submit once. Wait for the operation’s completed or failed state.
  5. Inspect the result and usage. Use the API or CLI for repeatable workloads after a successful test.

Check the result

The request returns a result and the wallet reflects the settled usage rather than an unexplained duplicate charge.

Troubleshooting

Unavailable models cannot accept paid requests. Reduce input or output size if limits are exceeded and report a request ID for a failed or stuck operation.

Next steps

Last updated October 12, 2026. Availability and prices are shown in the console before checkout.
Still need help? Open a support ticket with your service name, the time of the issue, and a redacted error message. Never include passwords or API keys.