LLM models
Gemini 3 Pro
On this page
Gemini 3 Pro — frontier reasoning and generation through one API.
| modelId | gemini-3-pro |
| Modality | text |
| Pricing | See this model on the Pricing page for the current per-call price (with your markup). |
Operations
| Operation | modelId | Endpoint | Required input |
|---|---|---|---|
| Default | gemini-3-pro | POST /api/v1/generate | prompt |
| Poll task | — | GET /api/v1/task/{id}?model=gemini-3-pro | — |
Input parameters
| Field | Type | Required | Values / example |
|---|---|---|---|
| prompt | string | Yes | Text value (default: Explain why autumn leaves change from green to gold and crimson before they fall, in three vivid sentences a curious child would love.) |
| memory | boolean | No | Automatically append previous messages to maintain multi-turn context. May increase token usage. (true/false) (default: false) |
| structured_outputs | boolean | No | Generate structured outputs (true/false) (default: false) |
| function_calling | boolean | No | Lets you define functions that Gemini can call (true/false) (default: false) |
| google_search | boolean | No | Use Google Search (true/false) (default: true) |
| thinking | boolean | No | Include the model's thinking process in the response (true/false) (default: true) |
| reasoning_effort | string | No | Control reasoning depth: Low for faster responses, High for deeper analysis (options: Low | High) (default: High) |
| system | string | No | System instruction for the model. Defaults to "You are Gemini 3 Pro, developed by Google." when omitted. |
Example request
bash
curl -X POST https://you.bot/api/v1/generate \
-H "Authorization: Bearer $YOUBOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"modelId":"gemini-3-pro","input":{"prompt":"Explain how diffusion models generate images, in two short sentences.","memory":false,"structured_outputs":false,"function_calling":false,"google_search":true,"thinking":true,"reasoning_effort":"High"}}'