I would like to request clarification on the following points:
-
The exact pricing and free tier limits for the following APIs:
-
Gemini 2.5 Flash
-
Gemini 1.5 Flash
-
Places API (new version)
-
Cloud Text-To-Speech
-
Cloud Speech-To-Text
-
-
I am confused in the pricing information for example of Gemini 1.5 Flash between the following sources:
-
On Google Cloud Console = “https://console.cloud.google.com/marketplace/product/google/generativelanguage.googleapis.com?q=sea…”
-
On Google AI for Developers = https://ai.google.dev/gemini-api/docs/pricing
-
-
At cloud console the pricing of input tokes on Gemini 1.5 flash is ₹6.61.. upto 128k count and ₹13.23.. after 128k count (What does count here mean?) this is getting me confused whether their is any free limit or not because the free tier limits mentioned in the Google AI for Developers documentation for Gemini 1.5 Flash are:
-
15 Requests per Minute (RPM)
-
250,000 Tokens per Minute (TPM)
-
50 Requests per Day (RPD)
Please clarify whether these limits are updated periodically or remain fixed.
-
-
Finally, does Google provide any built-in mechanism or service to automatically restrict or throttle API calls once the maximum RPM, TPM, or RPD limits are reached — to help avoid exceeding quotas or incurring extra charges?