Generate Sql Pricing & Token Calculator (Amazon)

Input / Prompt

—/ 1M tokens

Standard on-demand

Output / Completion

—/ 1M tokens

Standard on-demand

Prompt Cache Read

—/ 1M tokens

Optimized context reuse

Batch Inference

—/ 1M in

Save 50% via Batch API

Price Ratio

—

Prompt to completion factor

Regional Reach

16AWS Regions

Compare 16 regions ↓

Generate Sql 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(0% 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: —/1M · Output: —/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with Generate Sql on AWS

Prompt CachingSave ~0%

Caches repetitive system instructions, schemas, and document prefixes in memory with a 5-minute TTL.

Read Rate: — / 1M tokens
Write Rate: — / 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: — / 1M tokens
Batch Output: — / 1M tokens
Ideal for: Offline classification, synthetic data generation, benchmark evals

Cross-Region & Tiers16 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 16 available AWS cloud regions

Baseline: —/1M in16 Global Regions

AWS Region	Price Type	Rate	Unit
Asia Pacific (Tokyo)`ap-northeast-1`	other	$0.0020	Requests
Asia Pacific (Seoul)`ap-northeast-2`	other	$0.0020	Requests
Asia Pacific (Mumbai)`ap-south-1`	other	$0.0020	Requests
Asia Pacific (Singapore)`ap-southeast-1`	other	$0.0020	Requests
Asia Pacific (Sydney)`ap-southeast-2`	other	$0.0020	Requests
Canada (Central)`ca-central-1`	other	$0.0020	Requests
EU (Frankfurt)`eu-central-1`	other	$0.0020	Requests
Europe (Zurich)`eu-central-2`	other	$0.0020	Requests
EU (Ireland)`eu-west-1`	other	$0.0020	Requests
EU (London)`eu-west-2`	other	$0.0020	Requests
EU (Paris)`eu-west-3`	other	$0.0020	Requests
South America (Sao Paulo)`sa-east-1`	other	$0.0020	Requests
US East (N. Virginia)`us-east-1`	other	$0.0020	Requests
US East (Ohio)`us-east-2`	other	$0.0020	Requests
AWS GovCloud (US-East)`us-gov-east-1`	other	$0.0020	Requests
US West (Oregon)`us-west-2`	other	$0.0020	Requests

Developer Quickstart

Invoke Generate Sql 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="amazon.generate-sql-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of Generate Sql."}]
        }
    ],
    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")