Skip to content
Docs menu

LLM models

Gemini 3 Flash

On this page

Gemini 3 Flash — frontier reasoning and generation through one API.

modelIdgemini-3-flash
Modalitytext
PricingSee this model on the Pricing page for the current per-call price (with your markup).

Operations

OperationmodelIdEndpointRequired input
Defaultgemini-3-flashPOST /api/v1/generateprompt
Poll taskGET /api/v1/task/{id}?model=gemini-3-flash

Input parameters

FieldTypeRequiredValues / example
promptstringYesText value (default: In three vivid sentences, explain to a curious child why hot air balloons rise into the sky.)
memorybooleanNoAutomatically append previous messages to maintain multi-turn context. May increase token usage. (true/false) (default: false)
function_callingbooleanNoLets you define functions that Gemini can call (true/false) (default: false)
thinkingbooleanNoInclude the model's thinking process in the response (true/false) (default: true)
reasoning_effortstringNoControl reasoning depth: Low for faster responses, High for deeper analysis (options: Low | High) (default: High)
systemstringNoSystem instruction for the model. Defaults to "You are Gemini 3 Flash, 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-flash","input":{"prompt":"Explain how diffusion models generate images, in two short sentences.","memory":false,"function_calling":false,"thinking":true,"reasoning_effort":"High"}}'