Vision Languagetextimage

Gemini 3.5 Flash

Gemini 3.5 Flash is Google DeepMind's mid-2026 Flash-tier reasoning model, shipped May 19, 2026 at Google I/O on the Gemini 3 Flash foundation. It is natively multimodal, accepting text, images, audio, video and PDF input with a 1M-token context window and up to 64K output tokens, and supports adjustable thinking levels to trade quality against latency. It runs very fast (reported around 289 output tokens/sec) and posts strong agentic and coding benchmarks, in some cases beating 3.1 Pro, though it still trails Pro on the hardest reasoning tests. Ideal for high-volume agentic, coding and assistant workloads needing frontier-class quality without Pro-tier cost.

Input

Prompt

Top p

Reasoning

Temperature

Max completion tokens

1200000

Ready to generate

API Reference

POSThttps://api.token360.ai/v1/chat/completions

curl https://api.token360.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
  "model": "gemini-3.5-flash",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "temperature": 0.7,
  "top_p": 1,
  "max_completion_tokens": 4096
}'