How much does the Google API cost?

It depends on the model. Across the 5 models tracked here, input ranges from $0.1000 to $1.50 per million tokens and output from $0.4000 to $9.00. On a typical chat turn of 1,500 input and 300 output tokens the range is $0.000270 to $0.004950 per request.

What is the cheapest Google model?

Gemini 2.5 Flash-Lite, at $0.1000 per million input tokens and $0.4000 per million output. Whether it is cheap enough depends on whether it can do your task — the cost of finding out is usually a few cents.

How current is this Google pricing?

Every model entry stores the URL it was read from and the date it was read, both shown in the table above. The full data set was last reviewed on August 5, 2026. Prices change without notice, so verify against Google's own documentation before committing spend.

5 models tracked

Google API pricing

Google prices Gemini aggressively at the lower tiers and offers a free tier on several models, which makes it a common choice for high-volume, low-complexity work.

Models tracked: 5
Cheapest input: $0.1000
Highest input: $1.50
Exact token counts: 0 / 5

Every Google model, cheapest first

Google model pricing
Model	Input	Cached	Output	Context	Count	Chat turn
Gemini 2.5 Flash-Lite legacy	$0.1000	—	$0.4000	—	Estimate	$0.000270
Gemini 3.5 Flash-Lite	$0.3000	—	$2.50	—	Estimate	$0.001200
Gemini 2.5 Flash legacy	$0.3000	—	$2.50	1M	Estimate	$0.001200
Gemini 3.6 Flash	$1.50	—	$7.50	—	Estimate	$0.004500
Gemini 3.5 Flash	$1.50	—	$9.00	—	Estimate	$0.004950

Chat turn is 1,500 input and 300 output tokens. Prices read from Google’s pricing documentation; each row links to its own dated source.

What is distinctive about Google pricing

01
Several models have a free tier with rate limits, which is genuinely useful for prototyping and unusable for production.
02
Pricing on some models varies by input modality — audio input is priced separately from text and image on certain tiers.
03
Larger models use tiered pricing that changes above a context length threshold, so a long-context request can cost more per token than a short one.

Token counting on Google

Gemini uses a SentencePiece vocabulary shared with the Gemma open models. There is no browser build, so counts here are estimates; local tokenization is available in the Vertex AI SDKs for Python, Go and Java if you need precision from a backend.

Counts shown here for Google models are estimates and are labelled as such everywhere they appear. The methodology page documents every scaling factor used.

Compare with other providers

Or shortlist across all of them at once in the model finder, filtering by budget, context window and whether token counts can be exact.

Frequently asked questions

How much does the Google API cost?: It depends on the model. Across the 5 models tracked here, input ranges from $0.1000 to $1.50 per million tokens and output from $0.4000 to $9.00. On a typical chat turn of 1,500 input and 300 output tokens the range is $0.000270 to $0.004950 per request.
What is the cheapest Google model?: Gemini 2.5 Flash-Lite, at $0.1000 per million input tokens and $0.4000 per million output. Whether it is cheap enough depends on whether it can do your task — the cost of finding out is usually a few cents.
Can I count Google tokens exactly?: Not in a browser. Gemini uses a SentencePiece vocabulary shared with the Gemma open models. There is no browser build, so counts here are estimates; local tokenization is available in the Vertex AI SDKs for Python, Go and Java if you need precision from a backend. Counts shown on this site for Google models are labelled as estimates everywhere they appear.
How current is this Google pricing?: Every model entry stores the URL it was read from and the date it was read, both shown in the table above. The full data set was last reviewed on August 5, 2026. Prices change without notice, so verify against Google's own documentation before committing spend.