Foundation Model · Amazon BedrockGemma FamilyGeneral TierTextMulti-Tier Pricing

Gemma 4-E2B

Amazon Bedrock token pricing and cost optimization reference for Gemma 4-E2B.Rates normalized to USD per 1 Million Tokens ($/1M) with prompt caching and batch API discounts across 5 AWS regions.

ProviderGoogle

Maker HQMountain View, California, USA

Class / TierGeneral

ModalityText

Prompt CachingSave 75%

Batch APISave 50%

AWS Regions5 Global

Bedrock Model IDgoogle.gemma-4-e2b-v1:0

Input / Prompt

$0.04/ 1M tokens

$0.0000 per 1K tokens

Output / Completion

$0.08/ 1M tokens

$0.0001 per 1K tokens

Prompt Cache Read

$0.01/ 1M tokens

Save 75% vs prompt

Batch Inference

$0.02/ 1M in

Save 50% via Batch API

Price Ratio

1 : 2.0

Prompt to completion factor

Regional Reach

5AWS Regions

Compare 5 regions ↓

Alternatives to Gemma 4-E2B

Option	Price vs Gemma 4-E2B	Why look at it
Gemma 3 12B Compare →	input+125%+$0.05/1M output+262%+$0.21/1M Standard tier, per 1M tokens	Next step up in price from Google
Gemma 3 4B Compare →	inputsame price outputsame price Standard tier, per 1M tokens	Same Gemma line, different version
Gemma 4-26B-A4B Compare →	input+225%+$0.09/1M output+400%+$0.32/1M Standard tier, per 1M tokens	Also from Google
Gemma 4-31B Compare →	input+250%+$0.10/1M output+400%+$0.32/1M Standard tier, per 1M tokens	Also from Google (lightweight tier)

Gemma 4-E2B Spend Estimator

Model inference spend by prompt volume, cache hit rate, and batch processing.

Prompt Tokens (Millions / month)

M tokens

Completion Tokens (Millions / month)

M tokens

Prompt Cache Hit Rate(75% discount on cached context)

30%

Batch API Mode50% discount on non-realtime async jobs via S3

Estimated Monthly Spend

$0.00

Fresh Prompts:$0.00

Cached Prompts:$0.00

Completions:$0.00

Active: Input: $0.04/1M · Output: $0.08/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with Gemma 4-E2B on AWS

Prompt CachingSave ~75%

Caches repetitive system instructions, schemas, and document prefixes in memory with 5-minute and extended 1-hour TTL tiers.

Read Rate: $0.01 / 1M tokens
Write Rate (5m TTL): $0.05 / 1M tokens
Ideal for: Multi-turn conversations, RAG document queries, structured schemas

Batch InferenceSave 50%

Asynchronous bulk processing submitted via Amazon S3 with a standard 24-hour turnaround SLA.

Batch Input: $0.02 / 1M tokens
Batch Output: $0.04 / 1M tokens
Ideal for: Offline classification, synthetic data generation, benchmark evals

Cross-Region & Tiers5 Regions

AWS Bedrock supports standard on-demand inference, priority reserved throughput, and cross-region routing.

Standard: Lowest latency, pay-per-token with zero commitments
Cross-Region Routing: Automatically burst traffic to available regional capacity
GovCloud: Dedicated isolated compliance partitions with +20% uplift

Regional Pricing Matrix

Live rates across all 5 available AWS cloud regions

Baseline: $0.04/1M inGovCloud: $0.05/1M in5 Global Regions

AWS Region	Prompt Input $/1M	Completion Output $/1M	Cache Read $/1M	Batch Input $/1M	Pricing Tier
us-east-1 US East (N. Virginia)	$0.04	$0.08	—	$0.02	Baseline
us-west-2 US West (Oregon)	$0.04	$0.08	—	$0.02	Baseline
eu-central-1 EU (Frankfurt)	$0.05	$0.10	—	$0.02	+20% vs Baseline
us-gov-west-1 AWS GovCloud (US-West)	$0.05	$0.10	—	$0.02	GovCloud (+20%)
us-east-2 US East (Ohio)	$0.04	$0.08	—	$0.02	Baseline

Developer Quickstart

Invoke Gemma 4-E2B via Amazon Bedrock Converse API

Python (boto3) · Amazon Bedrock Runtime

import boto3

# Amazon Bedrock Converse API invocation
client = boto3.client("bedrock-runtime", region_name="us-east-1")

response = client.converse(
    modelId="google.gemma-4-e2b-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of Gemma 4-E2B."}]
        }
    ],
    inferenceConfig={
        "maxTokens": 1024,
        "temperature": 0.7
    }
)

output_text = response["output"]["message"]["content"][0]["text"]
usage = response["usage"]
print(f"Response: {output_text}")
print(f"Usage: {usage['inputTokens']} in, {usage['outputTokens']} out")