Flex inference

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

try:
    interaction = client.interactions.create(
        model="gemini-3-flash-preview",
        input="Analyze this dataset for trends...",
        service_tier='flex'
    )
    print(interaction.steps[-1].content[0].text)
except Exception as e:
    print(f"Flex request failed: {e}")

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from '@google/genai';

const client = new GoogleGenAI({});

async function main() {
    try {
        const interaction = await client.interactions.create({
            model: 'gemini-3-flash-preview',
            input: 'Analyze this dataset for trends...',
            service_tier: 'flex'
        });
        console.log(interaction.steps.at(-1).content[0].text);
    } catch (e) {
        console.log(`Flex request failed: ${e}`);
    }
}
await main();

# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Api-Revision: 2026-05-20" \
  -d '{
      "model": "gemini-3-flash-preview",
      "input": "Analyze this dataset for trends...",
      "service_tier": "flex"
  }'

from google import genai

client = genai.Client(http_options={"timeout": 900000})

try:
    interaction = client.interactions.create(
        model="gemini-3-flash-preview",
        input="why is the sky blue?",
        service_tier="flex",
    )
except Exception as e:
    print(f"Flex request failed: {e}")

import { GoogleGenAI } from '@google/genai';

const client = new GoogleGenAI({});

async function main() {
    try {
        const interaction = await client.interactions.create({
            model: "gemini-3-flash-preview",
            input: "why is the sky blue?",
            service_tier: "flex",
        }, {timeout: 900000});
    } catch (e) {
        console.log(`Flex request failed: ${e}`);
    }
}

await main();

import time
from google import genai

client = genai.Client()

def call_with_retry(max_retries=3, base_delay=5):
    for attempt in range(max_retries):
        try:
            return client.interactions.create(
                model="gemini-3-flash-preview",
                input="Analyze this batch statement.",
                service_tier="flex",
            )
        except Exception as e:
            if attempt < max_retries - 1:
                delay = base_delay * (2 ** attempt) # Exponential Backoff
                print(f"Flex busy, retrying in {delay}s...")
                time.sleep(delay)
            else:
                # Fallback to standard on last strike (Optional)
                print("Flex exhausted, falling back to Standard...")
                return client.interactions.create(
                    model="gemini-3-flash-preview",
                    input="Analyze this batch statement."
                )

# Usage
interaction = call_with_retry()
print(interaction.steps[-1].content[0].text)

import { GoogleGenAI } from '@google/genai';

const ai = new GoogleGenAI({});

async function sleep(ms) {
  return new Promise(resolve => setTimeout(resolve, ms));
}

async function callWithRetry(maxRetries = 3, baseDelay = 5) {
  for (let attempt = 0; attempt < maxRetries; attempt++) {
    try {
      console.log(`Attempt ${attempt + 1}: Calling Flex tier...`);
      const interaction = await ai.interactions.create({
        model: "gemini-3-flash-preview",
        input: "Analyze this batch statement.",
        service_tier: 'flex',
      });
      return interaction;
    } catch (e) {
      if (attempt < maxRetries - 1) {
        const delay = baseDelay * (2 ** attempt);
        console.log(`Flex busy, retrying in ${delay}s...`);
        await sleep(delay * 1000);
      } else {
        console.log("Flex exhausted, falling back to Standard...");
        return await ai.interactions.create({
          model: "gemini-3-flash-preview",
          input: "Analyze this batch statement.",
        });
      }
    }
  }
}

async function main() {
    const interaction = await callWithRetry();
    console.log(interaction.steps.at(-1).content[0].text);
}

await main();