Skip to content
ModelCap

Inference provider

Google: AI models and API pricing

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

Snapshot as of 19 November 2026

Google serves 38 tracked models through 58 endpoints as of 19 November 2026; the highest-ranked is Gemini 4 Carbon (ModelCap Index #1); mean measured uptime is 94.13%.

Models served
38
On the ModelCap Index
16
Cheapest output price
$0.36/1M

Language models on Google (33)

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

Language models served by Google, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1Gemini 4 CarbonGoogle#187.8$2.00$10.001M—100.0%2
2Gemini 4 NeonGoogle#287.2$3.00$15.001M—100.0%2
3Gemini 4 ArgonGoogle#386.6$2.00$10.001M—100.0%2
4Claude Opus 5.5Anthropic#485.8$4.00$20.001M—100.0%1
5Muse WonderMeta#585.6$4.00$20.001M—100.0%1
6Claude Fable 5.2Anthropic#684.2$8.00$40.001M—100.0%1
7Muse Spark 1.3Meta#782.4$1.25$4.251M—100.0%1
8Gemini 3.8 FlashGoogle#881.4$0.375$1.881M—75.00%3
9Gemini 4 HydrogenGoogle#980.4$1.50$7.501M—96.67%2
10Gemini 3.1 Pro PreviewGoogle#1679.2$1.00$6.001M—100.0%3
11Claude Sonnet 5.5Anthropic#2477.3$2.00$10.001M—100.0%1
12Gemini 3.5 Flash LiteGoogle#4171.1$0.15$1.251M—98.89%3
13Gemma 4 26B A4BGoogle#6065.9$0.15$0.60262K—0.00%1Open weights
14Muse EmberMeta#6365.2$0.10$0.501M—100.0%1
15Claude Haiku 5.5Anthropic#9358.3$0.10$0.501M—100.0%1
16gpt-oss-120bOpenAI#17439.8$0.09$0.36131K—96.67%1Open weights
17Claude Fable 5Anthropic—$10.00$50.001M——1
18Claude Fable 5.1Anthropic—$10.00$50.001M—100.0%1
19Claude Haiku 4.5Anthropic—$1.00$5.00200K—100.0%1
20Claude Opus 4.5Anthropic—$5.00$25.00200K——1
21Claude Opus 4.6Anthropic—$5.00$25.001M——1
22Claude Opus 4.7Anthropic—$5.00$25.001M—100.0%1
23Claude Opus 4.8Anthropic—$5.00$25.001M—100.0%1
24Claude Opus 5Anthropic—$5.00$25.001M——1
25Claude Sonnet 4.5Anthropic—$3.00$15.001M—100.0%1
26Claude Sonnet 4.6Anthropic—$3.00$15.001M—100.0%1
27Claude Sonnet 5Anthropic—$2.00$10.001M—100.0%1
28DeepSeek V4.1 FlashDeepSeek—$0.30$1.201M—100.0%1Open weights
29Gemini 3 Flash PreviewGoogle—$0.25$1.501M—100.0%3
30Gemini 3.1 Flash LiteGoogle—$0.125$0.751M—83.34%3
31Gemini 3.5 FlashGoogle—$0.75$4.501M—100.0%3
32Gemini 3.6 FlashGoogle—$0.375$1.881M—93.33%3
33Gemini 3.7 FlashGoogle—$0.375$1.881M—86.67%3

Image, audio and video models on Google (5)

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

Image, audio and video models served by Google
#ModelContextQuantizationUptime (30 min)Endpoints
1Nano Banana 2.1Google66K—100.0%1
2Nano Banana Pro (Gemini 3 Pro Image)Google66K—100.0%1
3Nano Banana 2 (Gemini 3.1 Flash Image)Google131K—100.0%1
4Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google66K—100.0%1
5Nano Banana (Gemini 2.5 Flash Image)Google33K—100.0%1

Google on ModelCap: common questions

How many AI models does Google serve?

38 tracked models as of 19 November 2026: 33 language models (16 with a public ModelCap Index position) and 5 image, audio or video models, across 58 live endpoints observed through OpenRouter.

What is the best model available on Google?

Gemini 4 Carbon from Google is the highest-ranked language model Google serves, at ModelCap Index position #1 and $10.00 per 1M output tokens on Google. The table lists every model in Index order.

What is the cheapest model on Google?

gpt-oss-120b at $0.36 per 1M output tokens ($0.09 per 1M input), the lowest positive language-token price Google lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which Google model has the largest context window?

Gemini 4 Carbon, served with a 1M-token context window on Google. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is Google?

Mean measured uptime across Google endpoints is 94.13% 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 prices come from?

From the OpenRouter catalogue entry for each Google endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Google 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 19 November 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