Skip to content
ModelCap

Inference provider

Google AI Studio: AI models and API pricing

Every tracked model Google AI Studio serves through OpenRouter, with Google AI Studio's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Rows link to the model page, where every provider's deployment is listed side by side.

Snapshot as of 1 October 2026

Google AI Studio serves 22 tracked models through 53 endpoints as of 1 October 2026; the highest-ranked is Gemini 3.8 Flash (ModelCap Index #9); mean measured uptime is 99.84%.

Models served
22
On the ModelCap Index
3
Cheapest output price
$0.20/1M

Language models on Google AI Studio (14)

Ranked models first, in ModelCap Index order. Prices are the lowest Google AI Studio lists for the model; the endpoint count shows how many deployments carry it.

Language models served by Google AI Studio, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1Gemini 3.8 FlashGoogle#982.7$0.375$1.881M—99.65%3
2Gemini 3.1 Pro PreviewGoogle#1279.8$1.00$6.001M—99.55%3
3Gemini 3.5 Flash LiteGoogle#3271.2$0.15$1.251M—100.0%3
4Gemini 2.5 FlashGoogle—$0.15$1.251M—100.0%3
5Gemini 2.5 Flash LiteGoogle—$0.05$0.201M—99.83%3
6Gemini 2.5 ProGoogle—$0.625$5.001M—99.25%3
7Gemini 2.5 Pro Preview 05-06Google—$0.625$5.001M—99.25%3
8Gemini 2.5 Pro Preview 06-05Google—$0.625$5.001M—99.25%3
9Gemini 3 Flash PreviewGoogle—$0.25$1.501M—100.0%3
10Gemini 3.1 Flash LiteGoogle—$0.125$0.751M—100.0%3
11Gemini 3.1 Flash Lite PreviewGoogle—$0.125$0.751M—99.84%3
12Gemini 3.5 FlashGoogle—$0.75$4.501M—100.0%3
13Gemini 3.6 FlashGoogle—$0.375$1.881M—100.0%3
14Gemini 3.7 FlashGoogle—$0.375$1.881M—100.0%3

Image, audio and video models on Google AI Studio (8)

Media models are ranked within their own catalogues; token prices do not apply.

Image, audio and video models served by Google AI Studio
#ModelContextQuantizationUptime (30 min)Endpoints
1Nano Banana Pro (Gemini 3 Pro Image)Google131K——1
2Nano Banana 2 (Gemini 3.1 Flash Image)Google66K——1
3Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google66K——1
4Nano Banana (Gemini 2.5 Flash Image)Google33K—100.0%3
5Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google66K—100.0%1
6Nano Banana Pro (Gemini 3 Pro Image Preview)Google66K—99.89%2
7Lyria 3 Pro PreviewGoogle1M—100.0%1
8Lyria 3 Clip PreviewGoogle1M——1

Google AI Studio on ModelCap: common questions

How many AI models does Google AI Studio serve?

22 tracked models as of 1 October 2026: 14 language models (3 with a public ModelCap Index position) and 8 image, audio or video models, across 53 live endpoints observed through OpenRouter.

What is the best model available on Google AI Studio?

Gemini 3.8 Flash from Google is the highest-ranked language model Google AI Studio serves, at ModelCap Index position #9 and $1.88 per 1M output tokens on Google AI Studio. The table lists every model in Index order.

What is the cheapest model on Google AI Studio?

Gemini 2.5 Flash Lite at $0.20 per 1M output tokens ($0.05 per 1M input), the lowest positive language-token price Google AI Studio lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which Google AI Studio model has the largest context window?

Gemini 3.8 Flash, served with a 1M-token context window on Google AI Studio. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is Google AI Studio?

Mean measured uptime across Google AI Studio endpoints is 99.84% over the last 30 minutes, as reported by OpenRouter at the time of the snapshot. Per-model uptime is in the table; it is a live operational signal, not a service-level guarantee.

Where do the Google AI Studio prices come from?

From the OpenRouter catalogue entry for each Google AI Studio endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Google AI Studio exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.

How current is this page?

This page uses the published ModelCap snapshot dated 1 October 2026. Publication and page updates happen separately. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further