Google · AI & LLMs

Google Gemini Live

Fast text generation with Gemini 1.5 Flash, or send an image URL alongside a prompt to Gemini 1.5 Pro for multimodal reasoning.

Endpoints

POST/v1/gemini/generate— Text generation with Flash or Pro.

POSTapi.apirunner.dev/v1/gemini/generate

idle

0 ms

Press Run to send the request.

curl -X POST "https://api.apirunner.dev/v1/gemini/generate" \
  -H "Authorization: Bearer YOUR_RUNNER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-1.5-flash",
    "prompt": "List three ways to cut p95 latency on an API gateway.",
    "max_output_tokens": 300
  }'

Parameters

Name	In	Type	Default	Notes
model	body	gemini-1.5-flash \| gemini-1.5-pro	gemini-1.5-flash	—
promptrequired	body	string	List three ways to cut p95 latency on an API gateway.	—
max_output_tokens	body	number	300	—