Foundation Model · Amazon BedrockImage
Titan Image Generator v2
Amazon Bedrock token pricing and cost optimization reference for Titan Image Generator v2.Live pricing reference across 2 AWS regions on Amazon Bedrock.
ProviderAmazon
ModalityImage
Prompt CachingSupported
Batch APISave 50%
AWS Regions2 Global
Bedrock Model ID
amazon.titan-image-generator-v2-v1:0Input / 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
Titan Image Generator v2 Spend Estimator
Model inference spend by prompt volume, cache hit rate, and batch processing.
M tokens
M tokens
30%
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 Titan Image Generator v2 on AWSPrompt 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 & Tiers2 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 2 available AWS cloud regionsBaseline: —/1M in2 Global Regions
| AWS Region | Price Type | Rate | Unit |
|---|---|---|---|
| image_generation | $0.0120 | image | |
| image_generation | $0.0100 | image | |
| image_generation | $0.0080 | image | |
| image_generation | $13.0000 | hour | |
| image_generation | $16.2000 | hour | |
| image_generation | $0.0050 | Images Processed | |
| image_generation | $1.9500 | Model/month | |
| image_generation | $23.4000 | hour | |
| image_generation | $16.8500 | hour | |
| image_generation | $21.0000 | hour | |
| image_generation | $13.0000 | hour | |
| image_generation | $0.0120 | image | |
| image_generation | $1.9500 | Model/month | |
| image_generation | $21.0000 | hour | |
| image_generation | $0.0080 | image | |
| image_generation | $16.8500 | hour | |
| image_generation | $23.4000 | hour | |
| image_generation | $0.0100 | image | |
| image_generation | $0.0050 | Images Processed | |
| image_generation | $16.2000 | hour |
No AWS regions found matching your filter.
Developer Quickstart
Invoke Titan Image Generator v2 via Amazon Bedrock Converse APIPython (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.titan-image-generator-v2-v1:0",
messages=[
{
"role": "user",
"content": [{"text": "Summarize key features and cost levers of Titan Image Generator v2."}]
}
],
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")