by Google DeepMind

Gemini 3.5 Flash.

multimodal closed 1M ctx
Cheapest input
$1.5/M
on DeepInfra
Cheapest output
$9.0/M
on DeepInfra
Hosted equiv.
~$3.24/hr
@ 100 tok/s on DeepInfra

Gemini 3.5 Flash is a deprecated Google model whose API requests now go to 3.6 Flash; it took text, image, video, audio and PDF input with a 1M-token limit.

Hosted API only

No self-host path — closed weights.

Gemini 3.5 Flash's weights aren't published. Use it via the access providers below.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
DeepInfra hosted inference $1.5 $9.0 Launch ↗
OpenRouter api aggregator $1.5 $9.0 Launch ↗
Family

Variants in the Gemini family.

Gemini 3.8 Flash
closed

Gemini 3.8 Flash is Google's most intelligent Flash model with significant ga...

Gemini 2.5 Pro
closed proprietary

Google's frontier reasoning model with native 1M-token context.

Gemini 1.5 Pro
closed proprietary

Google's pre-2.5 frontier — 2M context launched here.

Gemini 1.5 Flash
closed proprietary

Cheap fast Gemini — production default before 2.0/2.5 Flash.

Gemini 3.7 Flash
closed

Gemini 3.7 Flash is a deprecated Google model whose API requests now go to 3....

Gemini 3.5 Flash-Lite
closed

Gemini 3.5 Flash-Lite is a high-efficiency model from Google with upgraded ag...

Gemini 3.6 Flash
closed

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic w...

Gemini 2.0 Flash
closed

Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) com...

Gemini 2.0 Flash Lite
closed

Gemini 2.0 Flash Lite offers a significantly faster time to first token (TTFT...

Gemini 2.5 Flash
closed

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically d...

Gemini 2.5 Flash Lite
closed

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 fami...

Gemini 3.1 Flash Lite
closed

Gemini 3.1 Flash-Lite is Google's low-latency model for high-volume, lightwei...

Gemini 4 Argon
closed

Gemini 4 Argon is Google's flagship reasoning model, built for complex softwa...

Gemini 2.5 Flash Lite Preview 09-2025
closed

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 fami...

Gemini 2.5 Pro Preview 05-06
closed

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced re...

Gemini 3 Flash Preview
closed

Gemini 3 Flash Preview is a high speed, high value thinking model designed fo...

Gemini 3.1 Flash Lite Preview
closed

Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for...

Gemini 3.1 Pro Preview
closed

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhan...

Gemini 3.1 Pro Preview Custom Tools
closed

Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that impro...

FAQ

Frequently asked.

How do I run Gemini 3.5 Flash?
Gemini 3.5 Flash is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access Gemini 3.5 Flash?
Gemini 3.5 Flash is available via DeepInfra, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Gemini 3.5 Flash?
API pricing starts at $1.5/M input tokens and $9.0/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Gemini 3.5 Flash open-source or proprietary?
Gemini 3.5 Flash is a proprietary model from Google DeepMind. Access is API-only — there are no public weights to download.