Amazon Comprehend Pricing & Plans 2026

Name: Amazon Comprehend
Brand: Amazon Comprehend
Price: 12 USD
Availability: InStock

Complete pricing guide for Amazon Comprehend. Compare all plans, analyze costs, and find the perfect tier for your needs.

Try Amazon Comprehend Free →Compare Plans ↓

Not sure if free is enough? See our Free vs Paid comparison →
Still deciding? Read our full verdict on whether Amazon Comprehend is worth it →

🆓Free Tier Available

💎3 Paid Plans

⚡No Setup Fees

Choose Your Plan

Free Tier

Free for 12 months

✓50,000 units per month for each NLP API (entity recognition, sentiment, key phrases, language detection, syntax)
✓5,000 units per month for custom classification and custom entity recognition inference
✓Available for the first 12 months after AWS account creation
✓Full access to all standard API features during trial period

Start Free →

Standard NLP APIs (Pay-as-you-go)

From $0.0001/unit

✓Entity recognition, sentiment analysis, key phrase extraction at $0.0001 per unit (1 unit = 100 characters, minimum 3 units per request)
✓Language detection at $0.0001 per unit
✓Syntax analysis at $0.00005 per unit
✓PII detection and redaction at $0.0001 per unit
✓Volume discounts available at higher tiers (10M+ units)

Start Free Trial →

Custom Models

From $3/hr training + $0.50/hr endpoint

✓Custom classification model training at $3 per hour
✓Custom entity recognition model training at $3 per hour
✓Model endpoint hosting at $0.50 per hour ($360/month always-on)
✓Asynchronous custom inference also available per-unit
✓Model management and versioning included

Start Free Trial →

Comprehend Medical

From $0.01/unit

✓Medical named entity extraction (NERe) at $0.01 per unit
✓Medical ontology linking (ICD-10-CM, RxNorm, SNOMED CT)
✓HIPAA-eligible processing under AWS BAA
✓Supports clinical text, discharge summaries, and trial notes
✓Free tier: 25,000 units per month for first 12 months

Start Free Trial →

Pricing sourced from Amazon Comprehend · Last verified March 2026

Feature Comparison

Features	Free Tier	Standard NLP APIs (Pay-as-you-go)	Custom Models	Comprehend Medical
50,000 units per month for each NLP API (entity recognition, sentiment, key phrases, language detection, syntax)	✓	✓	✓	✓
5,000 units per month for custom classification and custom entity recognition inference	✓	✓	✓	✓
Available for the first 12 months after AWS account creation	✓	✓	✓	✓
Full access to all standard API features during trial period	✓	✓	✓	✓
Entity recognition, sentiment analysis, key phrase extraction at $0.0001 per unit (1 unit = 100 characters, minimum 3 units per request)	—	✓	✓	✓
Language detection at $0.0001 per unit	—	✓	✓	✓
Syntax analysis at $0.00005 per unit	—	✓	✓	✓
PII detection and redaction at $0.0001 per unit	—	✓	✓	✓
Volume discounts available at higher tiers (10M+ units)	—	✓	✓	✓
Custom classification model training at $3 per hour	—	—	✓	✓
Custom entity recognition model training at $3 per hour	—	—	✓	✓
Model endpoint hosting at $0.50 per hour ($360/month always-on)	—	—	✓	✓
Asynchronous custom inference also available per-unit	—	—	✓	✓
Model management and versioning included	—	—	✓	✓
Medical named entity extraction (NERe) at $0.01 per unit	—	—	—	✓
Medical ontology linking (ICD-10-CM, RxNorm, SNOMED CT)	—	—	—	✓
HIPAA-eligible processing under AWS BAA	—	—	—	✓
Supports clinical text, discharge summaries, and trial notes	—	—	—	✓
Free tier: 25,000 units per month for first 12 months	—	—	—	✓

Is Amazon Comprehend Worth It?

✅ Why Choose Amazon Comprehend

• Fully managed with no infrastructure to provision — scales automatically from a single document to millions via asynchronous batch jobs on S3
• Generous 12-month free tier covering 50,000 units per month across all standard APIs, making it easy to prototype and evaluate without upfront cost
• Deep AWS ecosystem integration with native S3, Lambda, CloudWatch, KMS, IAM, and 200+ other AWS service connections for building end-to-end pipelines
• Custom classification and entity recognition models can be trained without ML expertise using simple labeled CSV or augmented manifest files
• Comprehend Medical provides HIPAA-eligible medical NLP with ontology linking to ICD-10-CM, RxNorm, and SNOMED CT for healthcare use cases
• Built-in PII detection and redaction supporting 30+ entity types enables compliance workflows without custom regex or third-party tools

⚠️ Consider This

• Language support is uneven — many features only support English and a subset of other languages, limiting usefulness for global multilingual deployments
• Accuracy can vary significantly by domain; pre-trained models perform best on general-purpose text and may require custom training for specialized terminology
• Custom model endpoint pricing at $0.50/hour ($360/month) creates ongoing costs even during idle periods, making it expensive for intermittent or low-traffic workloads
• Vendor lock-in to AWS ecosystem — migrating NLP pipelines to another provider requires rewriting integrations, retraining custom models, and rearchitecting data flows
• No on-premises or edge deployment option; all processing requires sending data to AWS cloud endpoints, which may conflict with data residency or air-gapped requirements

What Users Say About Amazon Comprehend

👍 What Users Love

✓Fully managed with no infrastructure to provision — scales automatically from a single document to millions via asynchronous batch jobs on S3
✓Generous 12-month free tier covering 50,000 units per month across all standard APIs, making it easy to prototype and evaluate without upfront cost
✓Deep AWS ecosystem integration with native S3, Lambda, CloudWatch, KMS, IAM, and 200+ other AWS service connections for building end-to-end pipelines
✓Custom classification and entity recognition models can be trained without ML expertise using simple labeled CSV or augmented manifest files
✓Comprehend Medical provides HIPAA-eligible medical NLP with ontology linking to ICD-10-CM, RxNorm, and SNOMED CT for healthcare use cases
✓Built-in PII detection and redaction supporting 30+ entity types enables compliance workflows without custom regex or third-party tools

👎 Common Concerns

⚠Language support is uneven — many features only support English and a subset of other languages, limiting usefulness for global multilingual deployments
⚠Accuracy can vary significantly by domain; pre-trained models perform best on general-purpose text and may require custom training for specialized terminology
⚠Custom model endpoint pricing at $0.50/hour ($360/month) creates ongoing costs even during idle periods, making it expensive for intermittent or low-traffic workloads
⚠Vendor lock-in to AWS ecosystem — migrating NLP pipelines to another provider requires rewriting integrations, retraining custom models, and rearchitecting data flows
⚠No on-premises or edge deployment option; all processing requires sending data to AWS cloud endpoints, which may conflict with data residency or air-gapped requirements

Pricing FAQ

How much does Amazon Comprehend cost?

Amazon Comprehend offers multiple pricing tiers to suit different needs and budgets. They provide a free tier to get started, with paid plans offering additional features and higher usage limits. Check the current pricing page for the most up-to-date costs and features.

Does Amazon Comprehend have a free plan?

Yes, Amazon Comprehend offers a free plan that includes basic features. This allows you to test the platform and see if it meets your needs before upgrading to a paid plan with more advanced features.

What's included in each Amazon Comprehend pricing plan?

Each Amazon Comprehend pricing plan includes different feature sets, usage limits, and support levels. Higher-tier plans typically offer more advanced features, higher usage quotas, priority support, and additional integrations. Review the detailed comparison on their pricing page.

Can I change my Amazon Comprehend plan later?

Most SaaS tools including Amazon Comprehend allow you to upgrade or downgrade your plan as your needs change. Some changes take effect immediately, while others might apply at your next billing cycle. Check their billing settings or contact support for specific policies.

Ready to Get Started?

AI builders and operators use Amazon Comprehend to streamline their workflow.

Try Amazon Comprehend Now →

More about Amazon Comprehend

Review Alternatives Free vs Paid Pros & Cons Worth It?Tutorial

Choose Your Plan

Free Tier

Free for 12 months

✓50,000 units per month for each NLP API (entity recognition, sentiment, key phrases, language detection, syntax)
✓5,000 units per month for custom classification and custom entity recognition inference
✓Available for the first 12 months after AWS account creation
✓Full access to all standard API features during trial period

Start Free →

Standard NLP APIs (Pay-as-you-go)

From $0.0001/unit

✓Entity recognition, sentiment analysis, key phrase extraction at $0.0001 per unit (1 unit = 100 characters, minimum 3 units per request)
✓Language detection at $0.0001 per unit
✓Syntax analysis at $0.00005 per unit
✓PII detection and redaction at $0.0001 per unit
✓Volume discounts available at higher tiers (10M+ units)

Start Free Trial →

Custom Models

From $3/hr training + $0.50/hr endpoint

✓Custom classification model training at $3 per hour
✓Custom entity recognition model training at $3 per hour
✓Model endpoint hosting at $0.50 per hour ($360/month always-on)
✓Asynchronous custom inference also available per-unit
✓Model management and versioning included

Start Free Trial →

Comprehend Medical

From $0.01/unit

✓Medical named entity extraction (NERe) at $0.01 per unit
✓Medical ontology linking (ICD-10-CM, RxNorm, SNOMED CT)
✓HIPAA-eligible processing under AWS BAA
✓Supports clinical text, discharge summaries, and trial notes
✓Free tier: 25,000 units per month for first 12 months

Start Free Trial →

Pricing sourced from Amazon Comprehend · Last verified March 2026

Feature Comparison

Features	Free Tier	Standard NLP APIs (Pay-as-you-go)	Custom Models	Comprehend Medical
50,000 units per month for each NLP API (entity recognition, sentiment, key phrases, language detection, syntax)	✓	✓	✓	✓
5,000 units per month for custom classification and custom entity recognition inference	✓	✓	✓	✓
Available for the first 12 months after AWS account creation	✓	✓	✓	✓
Full access to all standard API features during trial period	✓	✓	✓	✓
Entity recognition, sentiment analysis, key phrase extraction at $0.0001 per unit (1 unit = 100 characters, minimum 3 units per request)	—	✓	✓	✓
Language detection at $0.0001 per unit	—	✓	✓	✓
Syntax analysis at $0.00005 per unit	—	✓	✓	✓
PII detection and redaction at $0.0001 per unit	—	✓	✓	✓
Volume discounts available at higher tiers (10M+ units)	—	✓	✓	✓
Custom classification model training at $3 per hour	—	—	✓	✓
Custom entity recognition model training at $3 per hour	—	—	✓	✓
Model endpoint hosting at $0.50 per hour ($360/month always-on)	—	—	✓	✓
Asynchronous custom inference also available per-unit	—	—	✓	✓
Model management and versioning included	—	—	✓	✓
Medical named entity extraction (NERe) at $0.01 per unit	—	—	—	✓
Medical ontology linking (ICD-10-CM, RxNorm, SNOMED CT)	—	—	—	✓
HIPAA-eligible processing under AWS BAA	—	—	—	✓
Supports clinical text, discharge summaries, and trial notes	—	—	—	✓
Free tier: 25,000 units per month for first 12 months	—	—	—	✓

Is Amazon Comprehend Worth It?

✅ Why Choose Amazon Comprehend

• Fully managed with no infrastructure to provision — scales automatically from a single document to millions via asynchronous batch jobs on S3
• Generous 12-month free tier covering 50,000 units per month across all standard APIs, making it easy to prototype and evaluate without upfront cost
• Deep AWS ecosystem integration with native S3, Lambda, CloudWatch, KMS, IAM, and 200+ other AWS service connections for building end-to-end pipelines
• Custom classification and entity recognition models can be trained without ML expertise using simple labeled CSV or augmented manifest files
• Comprehend Medical provides HIPAA-eligible medical NLP with ontology linking to ICD-10-CM, RxNorm, and SNOMED CT for healthcare use cases
• Built-in PII detection and redaction supporting 30+ entity types enables compliance workflows without custom regex or third-party tools

⚠️ Consider This

• Language support is uneven — many features only support English and a subset of other languages, limiting usefulness for global multilingual deployments
• Accuracy can vary significantly by domain; pre-trained models perform best on general-purpose text and may require custom training for specialized terminology
• Custom model endpoint pricing at $0.50/hour ($360/month) creates ongoing costs even during idle periods, making it expensive for intermittent or low-traffic workloads
• Vendor lock-in to AWS ecosystem — migrating NLP pipelines to another provider requires rewriting integrations, retraining custom models, and rearchitecting data flows
• No on-premises or edge deployment option; all processing requires sending data to AWS cloud endpoints, which may conflict with data residency or air-gapped requirements

What Users Say About Amazon Comprehend

👍 What Users Love

✓Fully managed with no infrastructure to provision — scales automatically from a single document to millions via asynchronous batch jobs on S3
✓Generous 12-month free tier covering 50,000 units per month across all standard APIs, making it easy to prototype and evaluate without upfront cost
✓Deep AWS ecosystem integration with native S3, Lambda, CloudWatch, KMS, IAM, and 200+ other AWS service connections for building end-to-end pipelines
✓Custom classification and entity recognition models can be trained without ML expertise using simple labeled CSV or augmented manifest files
✓Comprehend Medical provides HIPAA-eligible medical NLP with ontology linking to ICD-10-CM, RxNorm, and SNOMED CT for healthcare use cases
✓Built-in PII detection and redaction supporting 30+ entity types enables compliance workflows without custom regex or third-party tools

👎 Common Concerns

⚠Language support is uneven — many features only support English and a subset of other languages, limiting usefulness for global multilingual deployments
⚠Accuracy can vary significantly by domain; pre-trained models perform best on general-purpose text and may require custom training for specialized terminology
⚠Custom model endpoint pricing at $0.50/hour ($360/month) creates ongoing costs even during idle periods, making it expensive for intermittent or low-traffic workloads
⚠Vendor lock-in to AWS ecosystem — migrating NLP pipelines to another provider requires rewriting integrations, retraining custom models, and rearchitecting data flows
⚠No on-premises or edge deployment option; all processing requires sending data to AWS cloud endpoints, which may conflict with data residency or air-gapped requirements