Gemini 3.1 Pro Preview

Vertex AI · gemini-3.1-pro-preview

Gemini 3.1 Pro Preview from Vertex AI: $2 per million input tokens, $12 per million output tokens, $0.2 per million cached input tokens.

Prices in US dollars per million units
Rate	Price	Applies
Input	$2 per 1M input tokens	Ordinary
Cached input	$0.2 per 1M cached input tokens	Ordinary
Output	$12 per 1M output tokens	Ordinary
Input	$1 per 1M input tokens	BATCH tier
Input	$1 per 1M input tokens	FLEX tier
Input	$3.6 per 1M input tokens	PRIORITY tier
Input	$4 per 1M input tokens	prompts over 200,000 tokens
Input	$2 per 1M input tokens	BATCH tier, prompts over 200,000 tokens
Input	$7.2 per 1M input tokens	PRIORITY tier, prompts over 200,000 tokens
Cached input	$0.2 per 1M cached input tokens	BATCH tier
Cached input	$0.2 per 1M cached input tokens	FLEX tier
Cached input	$0.36 per 1M cached input tokens	PRIORITY tier
Cached input	$0.4 per 1M cached input tokens	prompts over 200,000 tokens
Cached input	$0.4 per 1M cached input tokens	BATCH tier, prompts over 200,000 tokens
Cached input	$0.72 per 1M cached input tokens	PRIORITY tier, prompts over 200,000 tokens
Cache write	$0.25 per 1M cache write tokens	prompts over 200,000 tokens
Output	$6 per 1M output tokens	BATCH tier
Output	$6 per 1M output tokens	FLEX tier
Output	$21.6 per 1M output tokens	PRIORITY tier
Output	$18 per 1M output tokens	prompts over 200,000 tokens
Output	$9 per 1M output tokens	BATCH tier, prompts over 200,000 tokens
Output	$32.4 per 1M output tokens	PRIORITY tier, prompts over 200,000 tokens