Text model API

Gemini 3.6 Flash API

google/gemini-3.6-flash is Google's latest high-efficiency multimodal AI model, designed for the agentic era with frontier-level intelligence at Flash speed. It delivers significant improvements in coding, reasoning, tool use, and multimodal understanding while reducing latency, token usage, and operational costs. With support for text, images, video, audio, and PDF inputs and an industry-leading 1 million-token context window, Gemini 3.6 Flash is ideal for AI assistants, enterprise automation, software engineering, and large-scale knowledge workflows. Built for developers and businesses, Gem

Model id
gemini-36-flash
Takes
Text (required)
Makes
Text
Endpoint
POST /api/v1/chat/completions
Made by
Google
Mode
Synchronous

Call Gemini 3.6 Flash

Base URL https://payload.rentprompts.com/api/v1. Replace the placeholder with your key.

Model gemini-36-flash

POST /api/v1/chat/completions

curl https://payload.rentprompts.com/api/v1/chat/completions \
  -H "Authorization: Bearer rp_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini-36-flash",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about APIs."
    }
  ],
  "max_tokens": 256
}'

Replace rp_live_YOUR_KEY with your key, ideally via the RENTPROMPTS_API_KEY environment variable. Keys are shown only once, so they are never filled in here. Get your API key →

What a typical call costs

Worked out from Gemini 3.6 Flash's published price (0.25 J in · 0.85 J out / 1K tokens). You pay only for successful results, from your Joule balance.
  • 1,000 input + 500 output tokens0.675 Joules
  • 10,000 input + 2,000 output tokens4.2 Joules

Send requests to POST /api/v1/chat/completions. Gemini 3.6 Flash answers synchronously: the result comes back in the response to the same request. Token counts come from the model's own usage report, so a real call may use more or fewer tokens than this example.

Settings

Optional parameters this model accepts (pass them in settings on /v1/run, or as top-level fields where OpenAI defines them).
NameTypeDefaultRange / options
temperatureinteger10 – 2
top_pfloat0.950 – 1
Gemini 3.6 Flash API — Pricing & Code Examples | RentPrompts