Using Vertex AI in Firebase requires that your Firebase project use the pay-as-you-go (Blaze) pricing plan.
Find the pricing for each model in the Google Cloud documentation.
Learn more about token limits per model.
We recommend doing the following to help manage your costs:
When using Gemini models, get an estimate of the token size and billable characters of your requests using the Count Tokens API.
Vertex AI Studio also provides a token estimate of your requests, even a visualization of the tokenization of your text prompt.
To avoid surprise bills, make sure that you monitor your costs and usage and set up budget alerts.