Foundation Model · Amazon BedrockTwelveLabs FamilyGeneral TierVideo

Pegasus 1.2

Amazon Bedrock token pricing and cost optimization reference for Pegasus 1.2.Rates normalized to USD per 1 Million Tokens ($/1M) with prompt caching and batch API discounts across 30 AWS regions.

ProviderTwelveLabs

Maker HQSan Francisco, California, USA

Class / TierGeneral

ModalityVideo

Prompt CachingSupported

Batch APISave 50%

AWS Regions30 Global

Bedrock Model IDtwelvelabs.pegasus-1-2-v1:0

Input / Prompt

—/ 1M tokens

Standard on-demand

Output / Completion

$7.50/ 1M tokens

$0.0075 per 1K tokens

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

30AWS Regions

Compare 30 regions ↓

Pegasus 1.2 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: $7.50/1M

Key Cost Levers & Architecture

Practical mechanisms to reduce inference costs with Pegasus 1.2 on AWS

Prompt CachingSave ~0%

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

Read Rate: — / 1M tokens
Write Rate (5m TTL): — / 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: $3.75 / 1M tokens
Ideal for: Offline classification, synthetic data generation, benchmark evals

Cross-Region & Tiers30 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 30 available AWS cloud regions

Baseline: —/1M in30 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)	—	$7.50	—	—	Baseline
us-west-2 US West (Oregon)	—	$7.50	—	—	Baseline
eu-central-1 Europe (Frankfurt)	—	$7.50	—	—	Baseline
eu-west-1 Europe (Ireland)	—	$7.50	—	—	Baseline
ap-northeast-1 Asia Pacific (Tokyo)	—	$7.50	—	—	Baseline
af-south-1 Africa (Cape Town)	—	$7.50	—	—	Baseline
ap-south-2 Asia Pacific (Hyderabad)	—	$7.50	—	—	Baseline
ap-southeast-3 Asia Pacific (Jakarta)	—	$7.50	—	—	Baseline
ap-southeast-5 Asia Pacific (Malaysia)	—	$7.50	—	—	Baseline
ap-southeast-4 Asia Pacific (Melbourne)	—	$7.50	—	—	Baseline
ap-south-1 Asia Pacific (Mumbai)	—	$7.50	—	—	Baseline
ap-northeast-3 Asia Pacific (Osaka)	—	$7.50	—	—	Baseline
ap-northeast-2 Asia Pacific (Seoul)	—	$7.50	—	—	Baseline
ap-east-2 Asia Pacific (Taipei)	—	$7.50	—	—	Baseline
ap-southeast-7 Asia Pacific (Thailand)	—	$7.50	—	—	Baseline
ca-central-1 Canada (Central)	—	$7.50	—	—	Baseline
ca-west-1 Canada West (Calgary)	—	$7.50	—	—	Baseline
eu-west-2 Europe (London)	—	$7.50	—	—	Baseline
eu-south-1 Europe (Milan)	—	$7.50	—	—	Baseline
eu-west-3 Europe (Paris)	—	$7.50	—	—	Baseline
eu-south-2 Europe (Spain)	—	$7.50	—	—	Baseline
eu-north-1 Europe (Stockholm)	—	$7.50	—	—	Baseline
eu-central-2 Europe (Zurich)	—	$7.50	—	—	Baseline
il-central-1 Israel (Tel Aviv)	—	$7.50	—	—	Baseline
mx-central-1 Mexico (Central)	—	$7.50	—	—	Baseline
me-south-1 Middle East (Bahrain)	—	$7.50	—	—	Baseline
me-central-1 Middle East (UAE)	—	$7.50	—	—	Baseline
sa-east-1 South America (Sao Paulo)	—	$7.50	—	—	Baseline
us-east-2 US East (Ohio)	—	$7.50	—	—	Baseline
us-west-1 US West (N. California)	—	$7.50	—	—	Baseline

Developer Quickstart

Invoke Pegasus 1.2 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="twelvelabs.pegasus-1-2-v1:0",
    messages=[
        {
            "role": "user",
            "content": [{"text": "Summarize key features and cost levers of Pegasus 1.2."}]
        }
    ],
    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")

Pegasus 1.2 Spend Estimator

Key Cost Levers & Architecture

Regional Pricing Matrix

Developer Quickstart

Other Models by TwelveLabs (3)