Gemini 3.6 Flash
by Google · Released 2026
Fast multimodal Gemini supporting the full minimal-to-high thinking ladder. Model id gemini-3.6-flash.
Gemini 3.6 Flash
Powered by Google · Proprietary multimodal transformer
Context Window
1M tokens
Parameters
Undisclosed
Max Output
65,536 tokens
Category
LLM Chat
Overview
Gemini 3.6 Flash is a fast multimodal model with a 1M-token context. Unlike 3.8 and 3.7 Flash, it accepts the complete thinking ladder including minimal, which makes it the cheapest 3.x Flash to run when you want reasoning effectively off.
Call model gemini-3.6-flash on /v1/chat/completions with reasoning_effort set to minimal for the lowest latency and token spend.
Input covers text, image, video, audio and PDF; output is text.
Pricing
| Metric | Price |
|---|---|
| Input /1M tokens | ₹150.0000 |
| Output /1M tokens | ₹750.0000 |
1 credit = ₹1 = $0.01 USD. Transparent per-call pricing — you pay only for what you call, with no seat fees or minimums.
Key Highlights
- 1,048,576-token context window
- Multimodal input: text, image, video, audio, PDF
- Function calling and structured outputs
- Thinking levels: minimal, low, medium, high
Technical Details
- Model id: gemini-3.6-flash
- Context window: 1,048,576 input / 65,536 output tokens
- Thinking levels accepted: minimal, low, medium, high
- Output pricing is inclusive of thinking tokens
Strengths
- 1M-token context at a competitive rate
- Native multimodal input without a separate vision model
Limitations
- Paid plans only
- Thinking tokens bill as output
Use Cases
API Example
curl https://api.callmissed.com/v1/chat/completions \
-H "Authorization: Bearer cm_YOUR_KEY" \
-d '{"model": "gemini-3.6-flash", "messages": [{"role": "user", "content": "Summarise this contract."}]}'Endpoint: POST /v1/chat/completions · Model ID: gemini-3.6-flash
Try Gemini 3.6 Flash now
Get 1000 free API credits on signup. No credit card required.