Gemini 3.7 Flash
Gemini 3.7 Flash is Google's workhorse multimodal LLM: send a prompt plus up to 11 images and get back copy, structured JSON, captions or analysis. Its sharpest edge over earlier Flash models is how closely it follows a brief — visual references, brand rules and dense documents — with a reasoning dial you set per call, from quick low-effort answers to careful multi-step work.
Input
The text prompt to send to the model. Pair with images for vision-language tasks or use alone for text-only generation.
Optional input images (up to 11, each ≤ 7 MB) to ground the prompt. Empty = text-only.
0 / 11
System instruction that sets the model's role and persistent behaviour (e.g. "You are a copy editor for an e-commerce catalogue").
How much the model reasons before answering. Low is fastest and cheapest, for captions and simple rewrites; medium suits most briefs; high is for multi-step analysis and dense documents.
Maximum tokens to generate. Cap low for short outputs (alt-text, captions) and high for long-form copy.
When true, the model returns structured JSON output. Pair with a JSON Schema in your prompt for the most reliable shape.
Output
Run the model to see output here.
Pricing
Features
API Examples
curl -X POST \
/api/v1/model/google/gemini-3.7-flash \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {}
}'