Gemini 3.8 Flash

Google Vertex AI
Geminitext

What does Gemini 3.8 Flash cost through Google Vertex AI?

Gemini 3.8 Flash through Google Vertex AI costs USD 0.75 per 1M input tokens and USD 3.75 per 1M output tokens for standard processing. Region: not stated. Input tier minimum: not stated; maximum: 200000 tokens. Price last verified (UTC): not stated.

How much do 1,000 requests to Gemini 3.8 Flash through Google Vertex AI cost?

For Gemini 3.8 Flash through Google Vertex AI, 1,000 requests with 1,000 input and 200 billed text output tokens each cost USD 1.5. Total: 1M input + 200,000 output tokens; cost = input rate × 1 + output rate × 0.2. This example uses standard processing and uncached text input. Reasoning tokens, taxes, tools, media and other fees are excluded; confirm the provider's terms and request limits.

This reference quote stays in the provider's published currency. Use the pricing table below for other currencies, tiers and regions.

Pricing
Input PriceOutput PriceCached Input
≤200K$0.75$3.75$0.075
>200K$0.75$3.75$0.075
Batch Input
$0.375
Batch Output
$1.88

per 1M tokens · USD

View official pricing →
Capabilities
Context—
Max Output—
Tools✓
Batch✓
Caching✓