LLM models
Gemini 3.1 Pro
On this page
Gemini 3.1 Pro — frontier reasoning and generation through one API.
| modelId | gemini-3-1-pro |
| Modality | text |
| Pricing | See this model on the Pricing page for the current per-call price (with your markup). |
Operations
| Operation | Endpoint | Description |
|---|---|---|
| Text to completion | POST /api/v1/generate | Base generation from a text prompt. |
| Poll task | GET /api/v1/task/{id}?model=gemini-3-1-pro | Retrieve state and result URLs. |
Input parameters
| Field | Type | Required | Values / example |
|---|---|---|---|
| prompt | textarea | required | Send a message |
| MODEL | text | optional | — |
| memory | select | optional | false, true |
| google_search | select | optional | false, true |
| thinking | select | optional | false, true |
| reasoning_effort | select | optional | Low, High |
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-3-1-pro","input":{"prompt":"Explain how honeybees tell the hive where flowers are, using one clear everyday analogy anyone can picture.","MODEL":"gemini-3.1-pro","memory":"false","google_search":"true","thinking":"true","reasoning_effort":"High"}}'