Gemini 3.8 Flash Pricing

Gemini 3.8 Flash is priced at $0.75 / $3.75 through December 31, 2026, and doubles to $1.50 / $7.50 on January 1, 2027.

Quick answer

Gemini 3.8 Flash costs $0.75 per 1M input tokens and $3.75 per 1M output tokens. 1,000 typical requests cost about $3.00.

Gemini 3.8 Flash API pricing

Price type	Now (USD per 1M tokens)	From January 1, 2027
Input	$0.75	$1.50
Cached input	$0.075	$0.15
Output	$3.75	$7.50
Batch input	$0.375	$0.75
Batch output	$1.88	$3.75

Output prices include thinking tokens. Explicit context caching also charges $0.50 per 1M tokens per hour of storage, rising to $1.00.

What Gemini 3.8 Flash costs in practice

Take a typical request with 2,000 input tokens and 400 output tokens. On Gemini 3.8 Flash:

1,000 requests cost $3.00 at standard prices.
1 million requests a month cost $3,000.
If half of each prompt is read from cache, 1,000 requests cost $2.33.
On the Batch API, with the same caching, they cost $1.16.

Price change: from January 1, 2027, the same 1 million requests cost $6,000 a month, 2x today's price. Plan your migration or caching work before then.

Cost calculator

Requests per month

Input tokens per request

Output tokens per request

Share of input read from cache (%)

Monthly cost, standard–

With your cache share–

On the Batch API–

Per 1,000 requests–

With apicuts: at least 20% less, after our fee–

Uses Gemini 3.8 Flash's standard prices checked October 30, 2026. Cache writes, thinking tokens and long-context tiers aren't included.

How to pay less for Gemini 3.8 Flash

Context caching cuts cached input to $0.075. Explicit caches also charge for storage per hour, so cache only what you reuse.
Batch Mode costs half the standard price.
Thinking tokens are billed as output, so set a thinking budget that fits the task.

apicuts switches these on for you, routes each request to the lowest-cost route that passes your quality checks, and guarantees at least 20% lower cost after our fee. See pricing.

Compare Gemini 3.8 Flash

See every model side by side in the LLM API pricing comparison, or read Gemini 3.8 Flash vs Claude Haiku 5.5.

Frequently asked questions

How much does Gemini 3.8 Flash cost?

Gemini 3.8 Flash costs $0.75 per 1M input tokens and $3.75 per 1M output tokens at standard prices, according to Google's Gemini API pricing page (checked October 30, 2026). From January 1, 2027 that rises to $1.50 and $7.50.

How much do 1,000 Gemini 3.8 Flash requests cost?

About $3.00, for requests of 2,000 input and 400 output tokens without caching.

Is there a cheaper way to use Gemini 3.8 Flash?

Yes: caching repeated prompt prefixes, moving work that can wait to the Batch API at half price, capping output length, and sending simpler requests to a cheaper model.

Sources: Google's Gemini API pricing page. Checked October 30, 2026.

Want us to find your 20%?

Book a free 15-minute API cost teardown. Bring last month's provider usage and we'll show you your biggest waste and the first fix we'd ship.

Get a Free 15-Minute API Cost Teardown