TechCompare LogoTechCompare

Gemini 3.5 Flash API Pricing & Cost Calculator

Separate token usage from cache storage and other services. Cached input and batch processing reduce token charges, but neither makes storing a large prefix free.

Gemini 3.5 Flash is Google's ultra-fast multimodal model, designed for extreme speed and high scalability.

By TechCompare · Updated

Input tokens
30,000
per request
Output tokens
3,000
per request
Volume
1,000 / monthly
Standard API

Calculator

Cost Comparison

Based on 30,000 input tokens (50% cached), 3,000 output tokens, and 1,000 requests.Provider USD token rates. Cache storage, cache writes, and other service fees aren't included.

Google: Gemini 3.5 Flash
$51.75
Same 30,000 in / 3,000 out (50% cached) scenario, pre-loaded. Adjust tokens, caching, or swap models.
Edit in the full tool

How this is calculated

Gemini 3.5 Flash standard token prices are $1.50/M input, $9/M output including thinking tokens, and $0.15/M cache reads. Cache reads are 90% below uncached input. Batch token rates are $0.75/$4.50/$0.075 per million. Google also charges $1 per million cached tokens per hour for storage. These direct Gemini API USD rates were checked on October 7, 2026.

Verdict

For 30K input, half cached, and 3K output, a standard request costs $0.05175 before storage. At 1,000 monthly requests, the chart shows $51.75. The same token usage in batch mode costs $25.875, rounded to $25.88, before storage. Storing a 30K-token cache for one hour adds $0.03 at the published storage rate. Use the actual cache size and retention time when estimating a complete bill.

More API Standalones scenarios

MiMo-V2.6-Pro Pricing
Cost calculator for this model
View details ➜
MiMo-V2.6-Flash Pricing
Cost calculator for this model
View details ➜
GLM-5.3-Flash Pricing
Cost calculator for this model
View details ➜

Related guides

Google's official Gemini pricing
Verify standard, batch, cache-read, and storage charges.
View guide ➜
Flash vs GPT-5.4 Mini
Compare current token costs and cache behavior.
View guide ➜

Frequently asked questions

Does Gemini 3.5 Flash support prompt caching?
Cache reads cost $0.15/M tokens at standard pricing, a 90% discount from $1.50/M uncached input. Google separately bills storage at $1 per million cached tokens per hour. The token chart excludes storage and other service charges.
How much does Gemini 3.5 Flash cost per million output tokens?
Standard output, including thinking tokens, costs $9/M. Batch output costs $4.50/M. Standard input is $1.50/M and cache reads are $0.15/M. Use the matching delivery mode for the whole token estimate.
Is Gemini 3.5 Flash cheaper than GPT-5.4 Mini?
For equal billed token counts, Mini costs half as much on standard input, output, and cache reads: $0.75/$4.50/$0.075 versus Gemini at $1.50/$9/$0.15 per million. Both offer 50% batch token discounts. Choose using supported inputs and accepted task results as well as the complete bill.

Related tools

LLM VRAM Calculator

Calculate the VRAM needed to run or fine-tune any LLM at any quantization.

Use tool ➜

Power Cost Estimator

Estimate annual electricity costs for your PC, Server, or TV.

Use tool ➜

Data Transfer Calculator

Estimate transfer times for files over USB, WiFi, Ethernet, and more.

Use tool ➜

JSON Formatter

Validate, format, and minify JSON data with readable output and error detection.

Use tool ➜