Gemini 3.6 Flash Twins Launch: Flagship and Lite Together

​

Key Takeaways

• Two models at once: Google’s July 2026 gemini-3.6-flash (multimodal flagship Flash) and gemini-3.5-flash-lite (high-frequency lightweight) are live on APIYI in the default / svip groups
• Fully tested on both endpoints: 30+ cases per model across the native Gemini format and the OpenAI-compatible format — Search grounding, Maps grounding, URL context, code execution, and Computer Use (3.6) all verified working, not just “listed”
• Official pricing: 3.6 Flash at $1.50 in / $7.50 out, 3.5 Flash-Lite at $0.30 in / $2.50 out (per 1M tokens, output includes thinking); discounts come from top-up bonuses (up to 20%, ≈17% off)
• Opposite thinking defaults: 3.6 thinks by default (four controllable tiers, 0–837 tokens measured); Lite ships with zero thinking and ~2s responses — this one line decides which to pick
• Same 1M context: both offer 1,048,576 input / 65,536 output with text/image/video/audio/PDF input

​

Background

​

Deep Dive

​

Verified capability matrix

​

Which one to pick?

• 3.6 Flash: deep reasoning, complex planning, heavy native-tool use, Computer Use
• 3.5 Flash-Lite: throughput-first workloads — high-frequency Q&A, classification, extraction, translation, support bots (about twice as fast, down to a fifth of the cost)

​

In Practice

curl -X POST "https://api.apiyi.com/v1beta/models/gemini-3.6-flash:generateContent" \
  -H "x-goog-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"parts": [{"text": "What was the most important AI release in July 2026?"}]}],
    "tools": [{"google_search": {}}]
  }'

from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.apiyi.com/v1")

response = client.chat.completions.create(
    model="gemini-3.5-flash-lite",
    messages=[{"role": "user", "content":
               "Classify this review as positive/negative/neutral: fast shipping, mediocre packaging"}]
)
print(response.choices[0].message.content)

​

Pricing & Availability

​

Summary