Gemini 3.5 Flash

Deprecated

Stable legacy Flash model for agentic and coding tasks.

Access details: Gemini API

The model ID to use in API requests.

gemini-3.5-flash

Updated Sep 23, 2026

Sources & notes

Capabilities & limits

Context window: 1M
Maximum output: 64K
Image input: Supported
Tool calling: Supported
Structured output: Supported

Pricing

USD / 1M tokens

Input: $1.50
Output: $9.00

Standard rates per million tokens. Discounts and long-context rates, where offered, are on Google's pricing page.

Full rate card 4 rates

All prices in USD.

Standard input

$1.50 per 1M tokens

Standard output

$9.00 per 1M tokens

includes thinking tokens

Cached input

$0.15 per 1M tokens

Cache storage

$1.00 per 1M tokens per hour

context caching storage

Paid tier. Batch: $0.75 input / $4.50 output / $0.075 cached. Flex: $0.75 / $4.50 / $0.08 cached. Priority: $2.70 / $16.20 / $0.27 cached. Free tier is free of charge. Grounding with Google Search: 5,000 free requests per month shared across Gemini 3.x models, then $14 per 1,000.

Price history

Sep 23, 2026

Input $1.50 per million tokens

Sep 23, 2026

Output $9.00 per million tokens

Technical details

Parameters: Not published
Active parameters: Not published
Architecture: Based on Gemini 3 Flash; part of the Gemini 3 Pro family, a sparse mixture-of-experts (MoE) transformer
Training / knowledge cutoff: January 2025
Input modalities: Text, image, video, audio, PDF
Output modalities: Text

From Google

Official announcement ↗

Release & lifecycle

First available: May 19, 2026
legacy: As of Sep 13, 2026
deprecated: As of Oct 20, 2026