Skip to content

Gemini 3.5 Flash

API pricing per million tokens

gemini-3-5-flash ReasoningChecked 24h ago
Input
$1.5
per 1M, list
Output
$9
per 1M tokens
Cached input
$0.15
batch $0.75 / $4.5
Context
1M
66K max output

Where to buy it (9)

  • Google Vertex AIglobal-flex-50%$0.75 / $4.5cached $0.075
  • Google Gemini APIflex-50%$0.75 / $4.5cached $0.075
  • Google Vertex AIglobal$1.5 / $9cached $0.15
  • Google Gemini API (list)the lab's own API$1.5 / $9cached $0.15
  • Google Vertex AIus+10%$1.65 / $9.9cached $0.165
  • Snowflake Cortex AI (AI_COMPLETE)default region, 0.9 AI Credits per 1M input tokens, 5.4 per 1M output tokens+20%$1.8 / $10.8$4.05 blended
  • Databricks Mosaic AI Gateway + Foundation Model APIsdefault region, 26.786 DBU per 1M input tokens, 160.714 DBU per 1M output tokens+25%$1.88 / $11.3$4.22 blended
  • Google Vertex AIglobal-priority+80%$2.7 / $16.2cached $0.27
  • Google Gemini APIpriority+80%$2.7 / $16.2cached $0.27

Through a gateway

Your own numbers

100M input and 20M output tokens a month: $330.00 direct.

Related models

About Gemini 3.5 Flash

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed.

Takes text, image, video, files, audio in and returns text. First listed May 20, 2026. Blended price $3.38 per 1M tokens at 3 input to 1 output. Overall score 3 on leadersboard.fru.dev (rank 35).

Questions

How much does Gemini 3.5 Flash cost?

$1.5 per million input tokens and $9 per million output tokens, with cached input at $0.15, or $0.75 and $4.5 through the Batch API.

What is the context window of Gemini 3.5 Flash?

1M tokens, with up to 66K tokens of output.

Where is Gemini 3.5 Flash cheapest?

Of 9 routes tracked, Google Vertex AI is cheapest at $0.75 input and $4.5 output per million tokens.

List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Weekly: LLM API list prices that changed, Thursday mornings.