# Amazon Comprehend vs spaCy

| Attribute | Amazon Comprehend | spaCy |
|---|---|---|
| **vioscaleAI score** | 53.1 (54% (medium)) | 54.3 (39% (low)) |
| activity.commits_last_30d | - | 13 |
| adoption.dependent_repos | - | 15,793 |
| adoption.github_stars | - | 33,966 |
| content.faq | `[{"answer":"A managed service offering access to multiple third-party foundation models for inference workloads, with support for fine-tuned custom models, batch processing at discounted rates, and retrieval-augmented generation through knowledge bases. It is indexed under NLP Apis.","source":"https://aws.amazon.com/bedrock/pricing/?nc2=h_pr_br","question":"What is Amazon Comprehend?","confidence":0.6},{"answer":"Amazon Comprehend offers a free tier, so you can start without paying. Paid plans are also available: On-Demand Standard Tier, Provisioned Throughput, Fine-Tuning Training and Batch Inference. Pricing changes often, so verify at source before relying on it.","source":"https://aws.amazon.com/bedrock/pricing/?nc2=h_pr_br","question":"Is Amazon Comprehend free?","confidence":0.6},{"answer":"Amazon Comprehend supports the web and a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.","source":"https://aws.amazon.com/bedrock/pricing/?nc2=h_pr_br","question":"What platforms does Amazon Comprehend support?","confidence":0.6},{"answer":"We have only confirmed a cloud / SaaS deployment for Amazon Comprehend, so it appears to be vendor-hosted. If a self-hosted option exists we have not found it documented publicly.","source":"https://aws.amazon.com/bedrock/pricing/?nc2=h_pr_br","question":"Can Amazon Comprehend be self-hosted?","confidence":0.6},{"answer":"We have independently confirmed HIPAA and GDPR for Amazon Comprehend. Certifications we do not list are ones we have not been able to verify from public sources, which is not the same as Amazon Comprehend not holding them. Always confirm compliance directly before you rely on it.","source":"https://aws.amazon.com/trust-center/?nc1=f_cc","question":"What security certifications does Amazon Comprehend have?","confidence":0.7},{"answer":"Amazon Comprehend is available worldwide. Its primary market is the United States.","source":"https://aws.amazon.com/bedrock/pricing/?nc2=h_pr_br","question":"Where is Amazon Comprehend available?","confidence":0.5}]` | `[{"answer":"An open-source natural language processing library designed for building real-world applications. It excels at large-scale information extraction and has become an industry standard since 2015 with a robust ecosystem of plugins. It is indexed under NLP Apis.","source":"https://spacy.io","question":"What is spaCy?","confidence":0.6},{"answer":"spaCy is open source, so it can be self-hosted and used at no licence cost. It is released under the MIT licence. Pricing changes often, so verify at source before relying on it.","source":"https://spacy.io","question":"Is spaCy free to use?","confidence":0.6},{"answer":"spaCy supports Windows, macOS, Linux and a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.","source":"https://spacy.io","question":"What platforms does spaCy support?","confidence":0.6},{"answer":"Yes. spaCy can be deployed on-premise and self-hosted, so it does not have to run on the vendor's infrastructure.","source":"https://spacy.io","question":"Can spaCy be self-hosted?","confidence":0.6},{"answer":"Yes. spaCy is published under the MIT licence, a permissive licence that generally allows commercial use and modification. Licence terms can change between releases, so verify against the repository for the version you intend to use.","source":"https://github.com/explosion/spaCy","question":"Is spaCy open source?","confidence":0.95}]` |
| deployment.options | `{"cloud":true}` | `{"self_hosted":true}` |
| description.long | Amazon Comprehend is an AWS managed service that analyzes unstructured text to identify entities, sentiment, key phrases, topics, language, and personally identifiable information. It offers pre-built APIs for common NLP tasks and custom model training capabilities for domain-specific document classification and entity extraction. | An open-source NLP framework for building and deploying language processing systems in production. Supports tokenization, text classification, neural model training, and includes tools for model management, packaging, and workflow automation. |
| features.capabilities | `{"open_source":false,"pricing_model":"usage-based-compute","batch_processing":true,"deployment_model":"cloud-api-only","real_time_latency":true,"custom_model_training":true,"domain_specific_models":true}` | `{"open_source":true,"pricing_model":"open-source-self-host","deployment_model":"both","embeddings_endpoint":true,"custom_model_training":true,"domain_specific_models":true}` |
| integrations.count | 2 | 2 |
| integrations.list | `[{"name":"Knowledge Bases","native":true,"category":"data|retrieval","direction":"inbound"},{"name":"Bedrock Data Automation","native":true,"category":"data_processing","direction":"inbound"}]` | `[{"name":"PyTorch"},{"name":"OpenAI"},{"name":"Hugging Face"}]` |
| language.primary | - | Python |
| license.spdx | - | MIT |
| market.availability | `{"primaryMarkets":["US"],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` | `{"primaryMarkets":[],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` |
| platform.support | `{"cli":true,"web":true}` | `{"cli":true,"mac":true,"linux":true,"windows":true}` |
| pricing | `{"type":"usage","plans":[{"free":true,"name":"Standard APIs","summary":"$0.0001 per unit (1 unit = 100 characters), 3-unit minimum per request. Free tier: 50K units/month for 12 months.","features":["Entity recognition","Sentiment analysis","Syntax analysis","Key phrase extraction","Language detection","Toxicity detection","Prompt safety classification","PII detection and redaction"],"components":[{"per":{"qty":1,"unit":"unit"},"kind":"metered","amount":0.0001,"currency":"USD"}],"description":"Pre-built entity recognition, sentiment analysis, syntax analysis, key phrase extraction, language detection, toxicity detection, and prompt safety classification","contactSales":false,"includedLimits":{"free_tier":"50K units per API per month for 12 months (5M characters)"}},{"free":false,"name":"Custom Classification and Entity Models","summary":"$3/hour for training, $0.50/month model management, $0.0005 per inference unit per second for real-time endpoints","features":["Custom model training","Asynchronous batch inference","Synchronous real-time inference with provisioned endpoints","Model management and storage"],"components":[{"kind":"fixed","amount":3,"period":"hour","currency":"USD"},{"kind":"fixed","amount":0.5,"period":"month","currency":"USD"},{"per":{"qty":1,"unit":"inference_unit_second"},"kind":"metered","amount":0.0005,"currency":"USD"}],"description":"Custom model training and inference for document classification and entity extraction","contactSales":false}],"summary":"Usage-based pricing starting at $0.0001 per unit for standard APIs. Free tier provides 50K units per API per month for 12 months. Custom models charged separately.","currency":"USD","freeTier":true,"sourceUrl":"https://aws.amazon.com/comprehend/pricing/","retrievedAt":"2026-09-28T13:18:29.350Z","startingPrice":{"amount":0.5,"period":"month","currency":"USD"},"billingPeriods":["month"]}` | `{"type":"open_source","summary":"Free, open-source library","freeTier":true,"sourceUrl":"https://spacy.io","retrievedAt":"2026-08-19T14:46:03.884Z"}` |
| pricing.free_tier | yes | yes |
| pricing.model | freemium | open_source |
| pricing.price_level | low | free |
| pricing.starting_price | `{"amount":0.5,"currency":"USD"}` | - |
| pricing.transparent | yes | yes |
| release.cadence_days | - | 20 |
| release.history | - | `[{"url":"https://github.com/explosion/spaCy/releases/tag/release-v3.8.16","date":"2026-08-24T10:01:11Z","type":"stable","version":"release-v3.8.16"},{"url":"https://github.com/explosion/spaCy/releases/tag/release-v3.8.15","date":"2026-08-07T17:13:19Z","type":"stable","version":"release-v3.8.15"},{"url":"https://github.com/explosion/spaCy/releases/tag/release-v3.8.14","date":"2026-03-29T07:47:14Z","type":"stable","version":"release-v3.8.14"},{"url":"https://github.com/explosion/spaCy/releases/tag/release-v3.8.13","date":"2026-03-23T17:40:51Z","type":"stable","version":"release-v3.8.13"},{"url":"https://github.com/explosion/spaCy/releases/tag/release-v3.8.12","date":"2026-03-23T13:33:37Z","type":"stable","version":"release-v3.8.12"},{"url":"https://github.com/explosion/spaCy/releases/tag/release-v3.8.11","date":"2025-11-17T20:37:38Z","type":"stable","version":"release-v3.8.11"},{"url":"https://github.com/explosion/spaCy/releases/tag/release-v3.8.10","date":"2025-11-17T15:54:29Z","type":"stable","version":"release-v3.8.10"},{"url":"https://github.com/explosion/spaCy/releases/tag/release-v3.8.9","date":"2025-11-13T14:57:22Z","type":"stable","version":"release-v3.8.9"},{"url":"https://github.com/explosion/spaCy/releases/tag/release-v3.8.8","date":"2025-11-07T09:26:30Z","type":"stable","version":"release-v3.8.8"},{"url":"https://github.com/explosion/spaCy/releases/tag/release-v3.8.7","date":"2025-05-23T08:53:14Z","type":"stable","version":"release-v3.8.7"},{"url":"https://github.com/explosion/spaCy/releases/tag/release-v3.8.6","date":"2025-05-19T07:52:28Z","type":"stable","version":"release-v3.8.6"},{"url":"https://github.com/explosion/spaCy/releases/tag/release-v3.8.3","date":"2024-12-11T13:11:38Z","type":"stable","version":"release-v3.8.3"},{"url":"https://github.com/explosion/spaCy/releases/tag/release-v3.8.2","date":"2024-10-01T18:19:33Z","type":"stable","version":"release-v3.8.2"},{"url":"https://github.com/explosion/spaCy/releases/tag/prerelease-v3.8.0.dev0","date":"2024-09-09T14:19:15Z","type":"prerelease","version":"prerelease-v3.8.0.dev0"},{"url":"https://github.com/explosion/spaCy/releases/tag/prerelease-v3.7.6a","date":"2024-08-20T10:09:49Z","type":"prerelease","version":"prerelease-v3.7.6a"},{"url":"https://github.com/explosion/spaCy/releases/tag/v3.7.5","date":"2024-06-05T07:57:36Z","type":"stable","version":"v3.7.5"},{"url":"https://github.com/explosion/spaCy/releases/tag/v3.7.4","date":"2024-02-15T19:16:59Z","type":"stable","version":"v3.7.4"},{"url":"https://github.com/explosion/spaCy/releases/tag/v3.7.2","date":"2023-10-16T16:11:22Z","type":"stable","version":"v3.7.2"},{"url":"https://github.com/explosion/spaCy/releases/tag/v3.7.1","date":"2023-10-05T06:46:15Z","type":"stable","version":"v3.7.1"},{"url":"https://github.com/explosion/spaCy/releases/tag/v3.7.0","date":"2023-10-02T09:10:08Z","type":"stable","version":"v3.7.0"}]` |
| security.certifications | `[{"name":"PCI DSS","status":"active"},{"name":"HIPAA/HITECH","status":"active"},{"name":"FedRAMP","status":"active"},{"name":"GDPR","status":"active"},{"name":"FIPS 140-3","status":"active"},{"name":"NIST 800-171","status":"active"}]` | - |
| security.disclosure_policy | yes | - |
| security.fedramp | yes | - |
| security.gdpr | yes | - |
| security.hipaa | yes | - |
| security.pci | yes | - |
| security.scorecard | - | 5.1 |
| security.trust_center | https://aws.amazon.com/compliance/ | - |
| security.vulnerabilities | - | `{"count":0,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=spacy&per_page=100","last_12m":0,"max_severity":null}` |

## Capabilities (NLP Apis)

| Capability | Amazon Comprehend | spaCy |
|---|:--:|:--:|
| **Capabilities** |  |  |
| Custom model training | ✓ | ✓ |
| Domain specific models | ✓ | ✓ |
| Deployment model | Cloud API only | Both |
| Batch processing | ✓ | - |
| Real time latency | ✓ | - |
| Embeddings endpoint | - | ✓ |
| Data residency EU | - | - |
| Open source | ✗ | ✓ |
| Pricing model | Usage based compute | Open source self host |

*Source: vioscaleAI. Generated 2026-10-16T23:23:45.731Z. "-" = undocumented, not absent.*