# Amazon Comprehend vs Stanford CoreNLP

| Attribute | Amazon Comprehend | Stanford CoreNLP |
|---|---|---|
| **Vioscale score** | 72.3 (33% (low)) | 44.7 (24% (low)) |
| activity.commits_last_30d | - | 0 |
| adoption.dependent_repos | - | 7 |
| adoption.github_stars | - | 10,102 |
| deployment.options | `{"cloud":true}` | `{"self_hosted":true}` |
| description.long | A machine learning service that processes text to identify entities, sentiment, topics, and key phrases. It supports both standard pre-built models and custom models trained on your own data, with APIs for document processing in multiple formats. | An open-source toolkit that analyzes text to extract linguistic features including word boundaries, grammatical tags, entities, dependency relationships, and semantic properties, supporting eight languages. |
| language.primary | - | Java |
| license.spdx | - | GPL-3.0 |
| market.availability | `{"hqCountry":"US","primaryMarkets":[],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` | - |
| platform.support | `{"cli":true,"web":true}` | `{"cli":true,"mac":true,"linux":true,"windows":true}` |
| pricing | `{"type":"usage","plans":[{"free":false,"name":"Standard APIs (Pay-per-use)","summary":"$0.0001 per unit (100 characters)","features":["Entity recognition","Sentiment analysis","Syntax analysis","Key phrase extraction","Language detection","Event detection","Toxicity detection","Prompt safety classification","PII detection","Redaction"],"components":[{"per":{"qty":1,"unit":"unit"},"kind":"metered","note":"1 unit = 100 characters, 3-unit minimum per request","amount":0.0001,"currency":"USD"}],"description":"Entity recognition, sentiment analysis, syntax analysis, key phrase extraction, language detection, event detection, toxicity detection, prompt safety","contactSales":false,"includedLimits":{"free_tier":"50k units/month for 12 months"}},{"free":false,"name":"Custom Classification & Entities","summary":"$3/hour training + $0.50/month management + $0.0003/unit inference","features":["Custom model training","Custom entity extraction","Custom text classification","Model management"],"components":[{"kind":"one_time","note":"Model training, billed by the second","amount":3,"period":"hour","currency":"USD"},{"kind":"fixed","note":"Custom model management","amount":0.5,"period":"month","currency":"USD"},{"per":{"qty":1,"unit":"unit"},"kind":"metered","note":"Async inference at 100 characters per unit, 3-unit minimum","amount":0.0003,"currency":"USD"}],"description":"Train custom NLP models to categorize text and extract domain-specific entities","contactSales":false},{"free":false,"name":"Managed Endpoints (Synchronous)","summary":"$0.0005 per second per Inference Unit","features":["Real-time synchronous inference","Scalable throughput with multiple IUs"],"components":[{"per":{"qty":1,"unit":"second","quantity":"per Inference Unit"},"kind":"metered","note":"1 IU = 100 characters/sec throughput, minimum 60 seconds per billing period","amount":0.0005,"currency":"USD"}],"description":"Real-time inference endpoints with provisioned throughput","contactSales":false}],"summary":"From $0.0001 per unit (100 characters) for standard APIs. Free tier: 50K units per month for 12 months.","currency":"USD","freeTier":true,"sourceUrl":"https://aws.amazon.com/comprehend/pricing/?pg=ln&sec=hs","retrievedAt":"2026-08-19T16:04:06.586Z","startingPrice":{"amount":0.5,"period":"month","currency":"USD"},"billingPeriods":["month"]}` | `{"type":"open_source","freeTier":true,"sourceUrl":"https://stanfordnlp.github.io/CoreNLP/","retrievedAt":"2026-08-19T16:05:04.600Z"}` |
| pricing.free_tier | yes | yes |
| pricing.model | freemium | commercial |
| pricing.price_level | low | free |
| pricing.starting_price | `{"amount":0.5,"currency":"USD"}` | - |
| pricing.transparent | yes | yes |
| release.cadence_days | - | 92 |
| release.history | - | `[{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.5.10","date":"2025-06-07T20:00:17Z","type":"stable","version":"v4.5.10"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.5.9","date":"2025-04-07T15:04:13Z","type":"stable","version":"v4.5.9"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.5.8","date":"2024-12-29T08:15:25Z","type":"stable","version":"v4.5.8"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.5.7","date":"2024-04-28T05:36:38Z","type":"stable","version":"v4.5.7"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.5.6","date":"2024-02-01T20:39:32Z","type":"stable","version":"v4.5.6"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.5.5","date":"2023-09-06T20:46:56Z","type":"stable","version":"v4.5.5"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.5.4","date":"2023-03-16T01:23:28Z","type":"stable","version":"v4.5.4"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.5.3","date":"2023-03-11T05:40:56Z","type":"stable","version":"v4.5.3"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.5.2","date":"2023-03-11T05:32:59Z","type":"stable","version":"v4.5.2"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.5.1","date":"2022-08-30T04:13:08Z","type":"stable","version":"v4.5.1"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.5.0","date":"2022-07-22T23:21:26Z","type":"stable","version":"v4.5.0"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.4.0","date":"2022-01-25T11:49:35Z","type":"stable","version":"v4.4.0"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.3.2","date":"2021-11-18T22:42:12Z","type":"stable","version":"v4.3.2"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.3.1","date":"2021-10-22T11:28:28Z","type":"stable","version":"v4.3.1"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.3.0","date":"2021-10-06T10:54:38Z","type":"stable","version":"v4.3.0"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.2.2","date":"2021-05-14T21:36:42Z","type":"stable","version":"v4.2.2"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.2.1","date":"2021-05-05T20:58:09Z","type":"stable","version":"v4.2.1"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.2.0","date":"2020-11-17T10:17:53Z","type":"stable","version":"v4.2.0"},{"url":"https://github.com/stanfordnlp/CoreNLP/releases/tag/v4.0.0","date":"2020-05-04T02:47:27Z","type":"stable","version":"v4.0.0"}]` |
| security.disclosure_policy | yes | - |
| security.fedramp | yes | - |
| security.gdpr | yes | - |
| security.hipaa | yes | - |
| security.pci | yes | - |
| security.scorecard | - | 2.6 |
| security.vulnerabilities | - | `{"count":0,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=maven&package_name=edu.stanford.nlp%3Astanford-kbp&per_page=100","last_12m":0,"max_severity":null}` |

## Capabilities (NLP Apis)

| Capability | Amazon Comprehend | Stanford CoreNLP |
|---|:--:|:--:|
| **Capabilities** |  |  |
| Custom model training | - | - |
| Domain specific models | - | - |
| Deployment model | - | - |
| Batch processing | - | - |
| Real time latency | - | - |
| Embeddings endpoint | - | - |
| Data residency EU | - | - |
| Open source | - | - |
| Pricing model | - | - |

*Source: Vioscale. Generated 2026-09-01T15:09:40.681Z. "-" = undocumented, not absent.*