GET STARTED

gemini-3.8-flash · API guide

Integrate gemini-3.8-flash through gemini. Request examples, parameters, authentication and result handling.

POST/v1beta/models/{model}:generateContent

Official reference gemini-3.8-flashChecked 2026-09-27Official docs

Integration flowFrom setup to your first request

Create an API key01
API_KEY
Create a key in the console and keep it on your server.
Choose a model02
Model ID + protocol
Check the model and input requirements in the live catalog.
Make your first call03
Request → response
Use the model’s request example and read the result.

Use the exact API model ID gemini-3.8-flash. This guide describes the platform contract; check the live catalog before calling the model.

Request example

The platform origin is filled in at build time. Set API_KEY to your server-side key before running.

curl "https://astralgames.ai/v1beta/models/gemini-3.8-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $API_KEY" \
  --data '{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Explain how an HTTP request works in three concise steps."
        }
      ]
    }
  ],
  "generationConfig": {
    "maxOutputTokens": 1024
  }
}'

Protocol and response

This model uses the gemini protocol. Read its native response and usage fields; do not wrap the request in the media task input envelope.

Supported endpoint templates：

POST /v1beta/models/{model}:generateContent
POST /v1beta/models/{model}:streamGenerateContent
POST /v1/interactions
POST /v1beta/interactions

Limit	Catalog value
Context tokens	128000
Maximum output tokens	16384

For streaming, use the native protocol streaming option and parse its events; check supported capabilities in the live catalog.

Official sources and identity

Checked: 2026-09-27 · Platform model: gemini-3.8-flash · Official reference: gemini-3.8-flash

Pricing and troubleshooting

Check current availability, contract and account pricing before integration. Keep request IDs and usage receipts when diagnosing errors. Complete API reference