Gemma 3 27B PT

Google · Active · available in 10 of 31 regions

VisionBatch inferenceStreaming Tool usePrompt cachingEmbeddingsFine-tuning
Context window
Max output
Input / 1M
$0.230
us-east-1
Output / 1M
$0.380

What Gemma 3 27B PT is good for

editorial

Gemma 3 27B PT offers image input, at the premium end of this provider’s range at $0.230 per 1M input tokens. Callable in 10 of 31 regions.

Suits

  • Images. Accepts image input: screenshots, scanned documents, charts and UI captures.
  • Bulk jobs. Batch inference is available, typically at half the on-demand rate, for work that can wait — backfills, nightly enrichment, evaluation runs.

Think twice if

  • Agentic loops. No prompt caching published, so every step re-pays full price for the prompt prefix. Expensive for agents that resend a long context.
  • Function calling. No tool use, so it cannot drive an agent loop or call your APIs — it answers from what is in the prompt.
  • High volume. At $0.230 per 1M input tokens it sits at the expensive end of the Google range. Worth it for hard tasks, wasteful for bulk extraction.

This section is judgement, not data from AWS. It is composed from the capabilities, context window, price position and region coverage shown elsewhere on this page — so it stays in step with the daily snapshot rather than going stale.

Model & inference profile IDs

Base model ID — direct on-demand invoke

Pricing by region

USD per 1M tokens
Region Input Output Cache read Cache write Batch in Batch out Source
us-east-1 US East (N. Virginia) $0.230 $0.380 $0.120 $0.190 API
us-east-2 US East (Ohio) $0.230 $0.380 $0.120 $0.190 API
us-west-2 US West (Oregon) $0.230 $0.380 $0.120 $0.190 API
eu-west-1 EU (Ireland) $0.270 $0.450 $0.140 $0.220 API
eu-west-2 EU (London) $0.360 $0.590 $0.180 $0.300 API
eu-south-1 EU (Milan) $0.270 $0.450 $0.140 $0.220 API
ap-northeast-1 Asia Pacific (Tokyo) $0.280 $0.460 $0.140 $0.230 API
ap-south-1 Asia Pacific (Mumbai) $0.270 $0.450 $0.140 $0.220 API
sa-east-1 South America (Sao Paulo) $0.280 $0.460 $0.140 $0.230 API

Region availability

TPM / RPM are default account quotas from AWS Service Quotas where a model-specific limit is published. They are per-account defaults and adjustable on request.

Where this model actually runs

Under a strict residency constraint, Gemma 3 27B PT can be served without the request leaving 9 of the 25 jurisdictions with a Bedrock region.

Gemma 3 27B PT appears in

Common questions

How much does Gemma 3 27B PT cost on Amazon Bedrock?
$0.230 per 1M input tokens and $0.380 per 1M output tokens in us-east-1.
Which AWS regions support Gemma 3 27B PT?
10 of 31 regions: us-east-1, us-east-2, us-west-2, eu-west-1, eu-west-2, eu-south-1, ap-northeast-1, ap-south-1, ap-southeast-2, sa-east-1.
What is the model ID for Gemma 3 27B PT on Bedrock?
google.gemma-3-27b-it.

Other Google models