How much does Summarize cost?

$0.04 per million input tokens and $0 per million output tokens. Prices as of Oct 21, 2026.

What is the context window of Summarize?

1M tokens, with up to 4K output tokens per response.

Images as input: yes. Tool calling: no. Structured (JSON) output: no. Reasoning mode: no.

Models with the same key capabilities for at least 20% less include Lyria 3 Clip Preview ($0 / $0), Lyria 3 Pro Preview ($0 / $0).

Scaledown

$0.04 per 1M input tokens and $0 per 1M output tokens · 1M context · vision.

Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026

$0.04

input / 1M tokens

output / 1M tokens

context window

max output

Estimated monthly bill for typical workloads. Try your own numbers in the cost calculator.

Workload	Per month
Customer chatbot 1,000 conversations a day, 8 turns each	$14.40
Document Q&A (RAG) 500 questions a day over retrieved documents	$3.60
Coding / tool-using agent 200 tasks a day, long tool-heavy contexts	$14.40
Content generation 30 long articles a day	$0.108
Classification / extraction 100,000 short items a day	$36.00

We started tracking Summarize on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.

Models with the same image input for at least 20% less (3:1 input/output mix), most capable first.

Cheaper alternatives to Summarize
Model	Input / 1M	Output / 1M	Context	Capabilities
Lyria 3 Clip Preview Google	$0	$0	1.05M	visionJSON
Lyria 3 Pro Preview Google	$0	$0	1.05M	visionJSON

For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $14.40 a month at list price without caching:

Option	Per month	You save
Move to Lyria 3 Clip Preview (similar capabilities)	$0	$14.40 (100%)

How much does Summarize cost?: $0.04 per million input tokens and $0 per million output tokens. Prices as of Oct 21, 2026.
What is the context window of Summarize?: 1M tokens, with up to 4K output tokens per response.
Does Summarize support images, tools and structured output?: Images as input: yes. Tool calling: no. Structured (JSON) output: no. Reasoning mode: no.
What are cheaper alternatives to Summarize?: Models with the same key capabilities for at least 20% less include Lyria 3 Clip Preview ($0 / $0), Lyria 3 Pro Preview ($0 / $0).