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. Rows link to the model page, where every provider's deployment is listed side by side.

Snapshot as of 1 October 2026

Google serves 45 tracked models through 100 endpoints as of 1 October 2026; the highest-ranked is Claude Sonnet 5.5 (ModelCap Index #1); mean measured uptime is 97.54%.

Models served

On the ModelCap Index

Cheapest output price

$0.25/1M

Language models on Google (41)

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
#	Model	ModelCap Index	Input $/1M	Output $/1M	Context	Quantization	Uptime (30 min)	Endpoints
1	Claude Sonnet 5.5Anthropic	#191.6	$2.00	$10.00	1M	—	100.0%	3
2	Claude Opus 5.5Anthropic	#288.0	$4.00	$20.00	1M	—	100.0%	3
3	Claude Fable 5.1Anthropic	#486.9	$10.00	$50.00	1M	—	99.87%	1
4	Gemini 3.8 FlashGoogle	#982.7	$0.375	$1.88	1M	—	99.14%	3
5	Gemini 3.1 Pro PreviewGoogle	#1279.8	$1.00	$6.00	1M	—	96.45%	3
6	Gemini 3.5 Flash LiteGoogle	#3271.2	$0.15	$1.25	1M	—	99.92%	5
7	Gemma 4 26B A4BGoogle	#4168.4	$0.15	$0.60	262K	—	77.40%	1Open weights
8	Kimi K2 ThinkingMoonshot AI	#5265.6	$0.60	$2.50	262K	—	—	1
9	Qwen3 235B A22B Instruct 2507Qwen	#6462.1	$0.22	$0.88	262K	—	99.70%	1Open weights
10	DeepSeek V3.2DeepSeek	#6661.7	$0.56	$1.68	164K	—	100.0%	1Open weights
11	Claude Haiku 4.5Anthropic	#7559.8	$1.00	$5.00	200K	—	99.87%	3
12	Qwen3 Next 80B A3B InstructQwen	#9854.7	$0.15	$1.20	262K	—	100.0%	1Open weights
13	Qwen3 Coder 480B A35BQwen	#11551.9	$0.22	$1.80	262K	—	99.16%	1Open weights
14	Qwen3 Next 80B A3B ThinkingQwen	#12746.9	$0.15	$1.20	262K	—	—	1Open weights
15	gpt-oss-120bOpenAI	#13244.6	$0.09	$0.36	131K	—	43.31%	1Open weights
16	gpt-oss-20bOpenAI	#16637.8	$0.07	$0.25	131K	—	99.91%	1Open weights
17	Llama 4 MaverickMeta	#17434.8	$0.35	$1.15	524K	—	—	1
18	Llama 4 ScoutMeta	#17732.9	$0.25	$0.70	1.3M	—	—	1
19	Llama 3.3 70B InstructMeta	#17832.4	$0.72	$0.72	128K	—	—	2
20	Claude Fable 5Anthropic	—	$10.00	$50.00	1M	—	—	2
21	Claude Opus 4.5Anthropic	—	$5.00	$25.00	200K	—	—	1
22	Claude Opus 4.6Anthropic	—	$5.00	$25.00	1M	—	—	2
23	Claude Opus 4.7Anthropic	—	$5.00	$25.00	1M	—	—	3
24	Claude Opus 4.8Anthropic	—	$5.00	$25.00	1M	—	100.0%	3
25	Claude Opus 5Anthropic	—	$5.00	$25.00	1M	—	100.0%	3
26	Claude Sonnet 4.5Anthropic	—	$3.00	$15.00	1M	—	—	2
27	Claude Sonnet 4.6Anthropic	—	$3.00	$15.00	1M	—	100.0%	3
28	Claude Sonnet 5Anthropic	—	$2.00	$10.00	1M	—	99.89%	3
29	DeepSeek V3.1DeepSeek	—	$0.60	$1.70	164K	—	—	1Open weights
30	Gemini 2.5 FlashGoogle	—	$0.30	$2.50	1M	—	90.61%	4
31	Gemini 2.5 Flash LiteGoogle	—	$0.10	$0.40	1M	—	99.34%	2
32	Gemini 2.5 ProGoogle	—	$1.25	$10.00	1M	—	98.55%	4
33	Gemini 2.5 Pro Preview 05-06Google	—	$1.25	$10.00	1M	—	98.55%	4
34	Gemini 2.5 Pro Preview 06-05Google	—	$1.25	$10.00	1M	—	98.55%	4
35	Gemini 3 Flash PreviewGoogle	—	$0.25	$1.50	1M	—	99.58%	3
36	Gemini 3.1 Flash LiteGoogle	—	$0.125	$0.75	1M	—	100.0%	5
37	Gemini 3.5 FlashGoogle	—	$0.75	$4.50	1M	—	99.80%	4
38	Gemini 3.6 FlashGoogle	—	$0.375	$1.88	1M	—	99.93%	4
39	Gemini 3.7 FlashGoogle	—	$0.375	$1.88	1M	—	97.57%	3
40	GLM 4.7Z.ai	—	$0.60	$2.20	200K	—	100.0%	1Open weights
41	MiniMax M2MiniMax	—	$0.30	$1.20	197K	—	—	1

Image, audio and video models on Google (4)

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

Image, audio and video models served by Google
#	Model	Context	Quantization	Uptime (30 min)	Endpoints
1	Nano Banana Pro (Gemini 3 Pro Image)Google	66K	—	100.0%	1
2	Nano Banana 2 (Gemini 3.1 Flash Image)Google	131K	—	100.0%	1
3	Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google	66K	—	100.0%	1
4	Nano Banana (Gemini 2.5 Flash Image)Google	33K	—	100.0%	1

Google on ModelCap: common questions

How many AI models does Google serve?

45 tracked models as of 1 October 2026: 41 language models (19 with a public ModelCap Index position) and 4 image, audio or video models, across 100 live endpoints observed through OpenRouter.

What is the best model available on Google?

Claude Sonnet 5.5 from Anthropic 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-20b at $0.25 per 1M output tokens ($0.07 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?

Llama 4 Scout, served with a 1.3M-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 97.54% 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 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.