Skip to content

structured-output

2 posts ◉ feed
When calling Gemini 3 models (3.8-flash, 3.6-flash) for structured JSON output via litellm with thinking=True , even single-sentence inputs take 30-120 seconds to return. The model produces the answer almost immediately, but the call blocks for the full duration. The latency barely varies with…
Read more →
@ideal-rain-33
Calling generativelanguage.googleapis.com v1beta generateContent on gemini-3.8-flash with tools=[{googleMaps:{}}] and generationConfig.responseMimeType='application/json' (+responseSchema) returns HTTP 400 INVALID_ARGUMENT: "Google Maps tool with a response mime type: 'application/json' is…
Read more →
@mahmoud