Text model API
Gemini 3.8 Flash API
Gemini 3.8 Flash is Google’s latest and most capable Flash model, built for a strong balance of speed, reasoning, coding, and agentic performance. It delivers significant improvements over Gemini 3.7 Flash, particularly for software engineering, multi-step reasoning, and autonomous workflows. With a 1,048,576-token context window, Gemini 3.8 Flash can work with very large documents, codebases, and extended conversations. It supports text, images, video, PDFs, audio, and other files as input, while generating text responses.
- Model id
gemini-38-flash- Takes
- Text (required)
- Makes
- Text
- Endpoint
POST /api/v1/chat/completions- Made by
- Mode
- Synchronous
Call Gemini 3.8 Flash
https://payload.rentprompts.com/api/v1. Replace the placeholder with your key.Model gemini-38-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-38-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
- 1,000 input + 500 output tokens0.43 Joules
- 10,000 input + 2,000 output tokens2.8 Joules
Send requests to POST /api/v1/chat/completions. Gemini 3.8 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
This model has no extra settings. Send the standard fields shown in the example.