Gemini 3.8 Flash

Name: Gemini 3.8 Flash API
Brand: Google Gemini API
Price: 0.75 USD

API pricing per million tokens

gemini-3-8-flash ReasoningChecked 5h ago

Cost calculator Compare Benchmarks

Input: $0.75; per 1M, list
Output: $3.75; per 1M tokens
Cached input: $0.075; batch $0.375 / $1.88
Context: 1M; 66K max output

Where to buy it (6)

Google Vertex AIglobal-flex-50%$0.375 / $1.88cached $0.037
Google Gemini APIflex-50%$0.375 / $1.88cached $0.037
Google Vertex AIglobal$0.75 / $3.75cached $0.075
Google Gemini API (list)the lab's own API$0.75 / $3.75cached $0.075
Google Vertex AIglobal-priority+80%$1.35 / $6.75cached $0.135
Google Gemini APIpriority+80%$1.35 / $6.75cached $0.135

Related models

ModelInputOutputCachedContextReleased

About Gemini 3.8 Flash

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Takes text, image, video, files, audio in and returns text. First listed Sep 2, 2026. Blended price $1.5 per 1M tokens at 3 input to 1 output. Overall score 15 on leadersboard.fru.dev (rank 13).

OpenRouter listing Google Gemini API pricing page

Across fru.devCompany profile 7 acquisitions Pay schedule 7 conferences

Questions

How much does Gemini 3.8 Flash cost?

$0.75 per million input tokens and $3.75 per million output tokens, with cached input at $0.075, or $0.375 and $1.88 through the Batch API.

What is the context window of Gemini 3.8 Flash?

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

Where is Gemini 3.8 Flash cheapest?

Of 6 routes tracked, Google Vertex AI is cheapest at $0.375 input and $1.88 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.

Where to buy it (6)

Through a gateway

Related models

About Gemini 3.8 Flash

Questions