Gemini 3.6 Flash

A previous-generation Gemini Flash model that remains available for production use, with a 1,048,576-token input limit.

Google describes it as
“sustained frontier-level intelligence optimized for real-world tasks at a higher speed and lower cost... excels at code generation, agentic execution, and spatial reasoning.”

Compare this model Check how your prompt fits this model’s context window

Last verified: Oct 31, 2026

Context window: 1,048,576
Max output: 65,536
Input price: $0.75
Output price: $3.75
Max input: 1,048,576
Released: Jul 21, 2026
Knowledge cutoff: Mar 2026
API model ID: gemini-3.6-flash

Google's page lists an input token limit of 1,048,576; it does not use the term context window.

About Gemini 3.6 Flash

Gemini 3.6 Flash is a previous-generation Flash model that Google says remains available for production use. Google describes it as offering sustained frontier-level intelligence for real-world tasks at a higher speed and lower cost, and as excelling at code generation, agentic execution and spatial reasoning. It takes text, image, video, audio and PDF input and returns text, at the same prices as Gemini 3.8 Flash.

API pricing

Per-token API prices from the provider's pricing page. Thresholds and processing modes are shown explicitly, not folded into one number.

Standard processing · USD per 1M tokens
Rate	Price
Input	$0.75
Cached input	$0.075
Output	$3.75
Cache storage, per 1M tokens per hour	$0.50

Batch processing · USD per 1M tokens
Rate	Price
Input	$0.375
Cached input	$0.0375
Output	$1.88
Cache storage, per 1M tokens per hour	$0.50

Priority processing · USD per 1M tokens
Rate	Price
Input	$1.35
Cached input	$0.135
Output	$6.75

Announced change · from Jan 1, 2027

Google's introductory pricing for Gemini 3.6 Flash ends on December 31, 2026. Standard processing then costs $1.50 input and $7.50 output per 1M tokens, with cached input at $0.15.

Output prices include thinking tokens.
Flex inference is priced the same as Batch.
Search grounding is billed separately: 5,000 requests per month free (shared across Gemini 3 and newer models), then $14 per 1,000 requests, capped at 1,500 requests per day.
Google lists no prompt-length threshold tier for this model.
A free tier is listed for Standard and Priority.

Modalities and capabilities

What the provider documents for this model. “API tool” means it needs a provider tool or endpoint rather than being native to the model.

Input modalities: Text, Image, Video, Audio, PDF
Output modalities: Text

ReasoningReasoning: ✓ Yes
Thinking is supported.
Tool / function callingTool / function calling: ✓ Yes
Structured outputsStructured outputs: ✓ Yes
Web searchWeb search: ✓ Yes · API tool
Grounding with Google Search.
Code executionCode execution: ✓ Yes · API tool
Computer useComputer use: ✓ Yes · API tool
Image generationImage generation: ✕ No
Google lists image generation as not supported for this model.
Prompt cachingPrompt caching: ✓ Yes
Batch APIBatch API: ✓ Yes

Benchmarks

Individual named benchmarks only: there is no overall score. Vendor-reported results come from the model maker's own launch materials. Scores from different sources, versions or settings are not directly comparable.

Benchmark results for Gemini 3.6 Flash
Benchmark	Score	Source type	Reported by
DeepSWEReported as 49% versus 37% for Gemini 3.5 Flash; the post gives no benchmark version.	49%	Vendor-reported	GoogleJul 21, 2026
GDPval-AA (v2)Reported as GDPval-AA v2, versus 1349 for Gemini 3.5 Flash.	1421	Vendor-reported	GoogleJul 21, 2026
OSWorld (Verified)Reported as OSWorld-Verified, versus 78.4% for Gemini 3.5 Flash.	83%	Vendor-reported	GoogleJul 21, 2026

Availability and API identifiers

Where Gemini 3.6 Flash is available and the identifier used there
Surface	Identifier
Gemini API	gemini-3.6-flash

Limitations and caveats

API vs. apps. These limits and prices describe the Gemini API model. The Gemini app and Google AI plans can apply different limits and are billed through subscriptions, not per token.

Google calls this a previous-generation Flash model; Gemini 3.5 Flash automatically routes to it. No shutdown date is announced.
Google lists introductory pricing that doubles on January 1, 2027; the current price shown depends on the date.
Google's model card gives a March 2026 knowledge cutoff and says knowledge in some domains may be limited to January 2025.

Sources

Last verified against these sources on Oct 31, 2026. Prices and limits change; follow the links for the live figure.

Gemini API docs — Gemini 3.6 Flash
Supports: status, context window, max input, max output, modalities, capabilities, pricing
OfficialChecked Oct 31, 2026
Gemini API — Models
Supports: status
OfficialChecked Oct 31, 2026
Gemini API — Pricing
Supports: pricing
OfficialChecked Oct 31, 2026
Gemini API — Deprecations
Supports: release date
OfficialChecked Oct 31, 2026
Google — Introducing Gemini 3.6 Flash and 3.5 Flash-Lite (Jul 21, 2026)
Supports: release date, benchmarks
Google blog post; scores are Google-reported, stated in the post text.
Vendor benchmarkChecked Oct 31, 2026
Google DeepMind model card — Gemini 3.6 Flash
Supports: knowledge cutoff
OfficialChecked Oct 31, 2026

Key facts