ModelPricing.aiGemini 3.5 Flash API Pricing
Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens on the Google Gemini API. Prices are tracked from the official Google Gemini pricing table and used by the ModelPricing.ai estimation API, so this page and the API always quote the same numbers. See all Google Gemini model pricing or the full LLM pricing comparison.
Gemini 3.5 Flash Pricing Per Million Tokens
| Tier | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|
| Standard | $1.50 | $9.00 | $0.150 | — |
What Gemini 3.5 Flash Costs In Practice
Monthly cost at three representative workloads, using the standard text rate in effect today.
| Workload | Monthly cost |
|---|---|
| Light — 1M in / 200K out | $3.30 |
| Moderate — 10M in / 2M out | $33.00 |
| Heavy — 100M in / 20M out | $330.00 |
Need your own numbers? Use the LLM cost calculator or call the estimation API directly.
Compare Gemini 3.5 Flash With Other Models
Looking for something cheaper from Google Gemini? Gemini 2.0 Flash Lite is the lowest-priced option on input tokens.
Gemini 3.5 Flash Pricing FAQ
How much does Gemini 3.5 Flash cost per token?
Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens on the Google Gemini API. That works out to $0.0015 per thousand input tokens.
How much does it cost to run Gemini 3.5 Flash per month?
At 1M in / 200K out per month, Gemini 3.5 Flash costs about $3.30. A heavier workload of 100M input and 20M output tokens costs about $330.00.
Does Gemini 3.5 Flash support prompt caching?
Yes. Cached input tokens are billed at $0.150 per million on Gemini 3.5 Flash, compared with $1.50 per million for uncached input.
Estimate Gemini 3.5 Flash costs programmatically
POST a token count to /v1/estimate with model gemini-3.5-flash and get a priced breakdown back, promotions
already applied.