Gemini 3.6 Flash Tiered
⧉The dynamic thinking tier of Gemini 3.6 Flash: no fixed thinking budget -- the model decides how much to think from the difficulty of each question, answering simple ones fast and thinking longer on hard ones. Ideal for mixed traffic of uneven difficulty. Set model to gemini-3.6-flash-tiered.
Live Test · Playground
Try out Gemini 3.6 Flash Tiered right here (available after login)。
Input
Advanced
Conversation
About Gemini 3.6 Flash Tiered
The dynamic thinking tier of Gemini 3.6 Flash: no fixed thinking budget, the model decides how much to think from the difficulty of each question, answering simple ones fast and thinking longer on hard ones, ideal for mixed traffic of uneven difficulty. 1M-token context, image input, same price as the other tiers. Set model to gemini-3.6-flash-tiered.
Use cases
When one endpoint serves both simple questions and complex reasoning, let the model decide how much to think.
End-user chat assistants face unpredictable question types; automatic tiering is the least hassle.
Agent steps differ in difficulty; Tiered spares you from picking a tier for each one.
How to choose
Unsure how hard your traffic is? Pick Tiered. Clearly simple goes to Low, clearly complex to High, and the standard tier gives a steady, predictable amount of thinking.
FAQ
How is the thinking amount decided?
How is it priced?
How large is the context window?
Am I charged for failed calls?
Related Models
Explore other models you can integrate.
GPT-5.6 Sol
Frontier flagship for agentic coding
GPT-5.6 Terra
Balanced everyday agentic coding model
GPT-5.6 Luna
Fast, economical agentic coding model
GPT-5.5
Flagship chat and reasoning model
GPT-6 Astra
Next-generation OpenAI flagship - 1.05M context
GPT Image 2
High-quality text-to-image / image-to-image model
GPT Image 2.5 Flare
Next-gen image model - clean and smooth
GPT Image 2.5 Sunburst
Next-gen image model - richer texture
Nano Banana 2
High-quality text-to-image / image-to-image model
Nano Banana Pro
Flagship text-to-image / image-to-image model
Claude Sonnet 4.6
Balanced, efficient chat and coding model
Claude Opus 5
Next-generation flagship from Anthropic
Claude Fable 5
Anthropic Fable series · narrative and long-form writing
Gemini 3.1 Pro
Next-generation flagship reasoning model from Google
Gemini 3.8 Flash
Latest Flash · adaptive thinking
Gemini 3.7 Flash
Previous Flash · adaptive thinking
Gemini 3.6 Flash
Next-generation fast thinking model · four thinking budgets
Gemini 3.6 Flash High
Deep thinking tier
Gemini 3.6 Flash Low
Fastest, lowest-cost tier
Gemini 3 Flash
Fast, low-latency, cost-efficient chat model
Gemini 3.5 Flash
Next-generation fast thinking model
Gemini 2.5 Flash
Fast, low-latency, cost-efficient chat
Veo 3.1
Text / image to video · multiple tiers · multiple resolutions
Seedance 2.5
Text / image to video · up to 30 seconds
Seedance 2.0
Text / image to video · 5-15 seconds
Seedance 2.0 Fast
Low latency · lowest cost
Seedance 2.0 Mini
Entry tier · lowest cost
Wan 3.0
One endpoint, five modes · up to 30 seconds
Wan 3.0 Prime
Same capabilities · several times faster
MiniMax H3
1080P · native audio
Grok Imagine Video 1.5
Billed per clip · up to 15 seconds
