Gemini 3.6 Flash

Latest Flash generation. Native multimodal, 1M context, integrated hybrid reasoning.

ChatGoogle1M tokens$1.6351 / $8.1754 · 1M

google/gemini-3.6-flash

Context
1M tokens
Completion cap
65,536
Tools
Yes
JSON
Yes
Released
2026-07-21
ZDR
Verified

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.6-flash",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Gemini 3.6 Flash?
Latest Flash generation. Native multimodal, 1M context, integrated hybrid reasoning. Gemini 3.6 Flash runs on the Geek Hub API (OpenAI-compatible). Model id: google/gemini-3.6-flash.
Is Gemini 3.6 Flash free?
No. Input is $1.6351 per 1M tokens and output is $8.1754 per 1M tokens on Geek Hub (markup included).
What is the context length of Gemini 3.6 Flash?
Gemini 3.6 Flash has a 1M tokens context window. It supports up to 65,536 completion tokens.
Does Gemini 3.6 Flash support tool calling and structured outputs?
Gemini 3.6 Flash accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Gemini 3.6 Flash released?
Gemini 3.6 Flash was released on 2026-07-21.

More models from Google