Grigory, is this true even when accessing Gemini 2.x models through Google AI Studio?
"It’s a pity that the capability support across the Gemini family is uneven, PDFs are supported only in 2.0 Flash, reasoning is supported only by a different Flash Thinking model, and content caching is only supported by the 1.5 family."
Grigory, is this true even when accessing Gemini 2.x models through Google AI Studio?
"It’s a pity that the capability support across the Gemini family is uneven, PDFs are supported only in 2.0 Flash, reasoning is supported only by a different Flash Thinking model, and content caching is only supported by the 1.5 family."
I didn't check the Gemini API yet. There may be a difference compared to Vertex AI, but in general I do not expect significant difference