{ "data": { "a": { "slug": "amazon-nova-embeddings", "name": "Amazon Nova Multimodal Embeddings", "vendor": "Amazon Web Services", "vendorUrl": "https://aws.amazon.com/nova/", "kind": "http-api", "category": "embeddings", "summary": "Amazon Nova Multimodal Embeddings is an AWS model on Amazon Bedrock that turns text, images, document images, video and audio into vectors in one space, at 256, 384, 1024 or 3072 dimensions, through synchronous and asynchronous calls.", "url": "https://www.anchorterminal.com/tools/amazon-nova-embeddings", "markdownUrl": "https://www.anchorterminal.com/tools/amazon-nova-embeddings.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/amazon-nova-embeddings.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/amazon-nova-embeddings.json", "license": "Proprietary service under the AWS Service Terms. The AWS SDKs are Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://bedrock-runtime.us-east-1.amazonaws.com", "packages": [ { "registry": "pypi", "name": "boto3" }, { "registry": "npm", "name": "@aws-sdk/client-bedrock-runtime" } ], "auth": "api-key", "authNotes": "AWS Signature Version 4 with IAM credentials or a role, or an Amazon Bedrock API key sent as a bearer token (`AWS_BEARER_TOKEN_BEDROCK`). Short-term keys last up to 12 hours and inherit the caller's IAM permissions. Long-term keys create an IAM user and AWS recommends them for exploration only. Access is self-serve once a person has an AWS account, and asynchronous calls also need write access to an S3 bucket (https://docs.aws.amazon.com/bedrock/latest/userguide/api-keys.html).", "pricing": "usage", "pricingNotes": "On demand in US East (N. Virginia), text input is $0.135 per million tokens, a standard image $0.00006, a document image $0.0006, video $0.0007 a second and audio $0.00014 a second. Batch is $0.0675 per million text tokens, with lower media rates. GovCloud prices are 20 per cent higher. There is no model-specific free tier. New AWS accounts can receive up to $200 in Free Tier credits, which lets an agent's owner start without a contract (https://aws.amazon.com/bedrock/pricing/).", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Nova guide, the Bedrock model card or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 18066100, "pypiWeekly": 573748207, "asOf": "2026-10-08" }, "docsUrl": "https://docs.aws.amazon.com/nova/latest/userguide/nova-embeddings.html", "llmsTxt": "https://docs.aws.amazon.com/nova/latest/userguide/llms.txt", "capabilities": [ "embed.text", "embed.multimodal" ], "tags": [ "official", "hosted", "usage-priced", "closed-source", "python", "typescript", "llms-txt", "batch", "async-jobs", "enterprise" ], "lastRelease": "2025-10-28", "graded": true, "anchor": { "graded": true, "score": 75, "grade": "BB", "agentReady": true, "rank": 59, "ranked": true, "rankOf": 842, "categoryRank": 1, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 78, "maintenance": 50, "payments": 30, "reliability": 95, "schema": 76, "security": 91, "transparency": 79 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "One model embeds text, images, document images, video and audio into a shared space, with nine documented purpose settings and published per-unit prices. It runs in US East (N. Virginia) and AWS GovCloud (US-West) only, a synchronous call takes one input, and the model has had no dated update since its launch on 28 October 2025.", "bestFor": "Suited to mixed-media retrieval for teams already on AWS, especially video and audio archives processed through S3.", "strengths": [ "Text, images, document images, video and audio share one vector space, with four output sizes from 256 to 3072", "`embeddingPurpose` has nine documented values, with separate settings for indexing and for each retrieval type", "Published quotas of 2,000 requests a minute and 30 concurrent asynchronous jobs per Region", "Bedrock stores no model inputs or outputs by default, and this model is not on the abuse-detection retention list", "The asynchronous API segments long text, audio and video itself and writes one embedding per segment to S3" ], "weaknesses": [ "In-Region inference in us-east-1 and us-gov-west-1 only, with no cross-Region inference profile", "A synchronous request embeds one item, with at most 8,192 characters of inline text or 30 seconds of audio or video", "The Bedrock model card marks Invoke as unsupported while the Nova guide documents `InvokeModel` for synchronous calls", "No dated change to the model was found after its launch on 28 October 2025", "Both quotas are marked not adjustable through Service Quotas" ], "agentNotes": [ "Call `bedrock-runtime` in us-east-1 with model ID `amazon.nova-2-multimodal-embeddings-v1:0`. No other commercial Region serves it", "Index with `embeddingPurpose` `GENERIC_INDEX`, then embed queries with the retrieval value that matches the index, such as `TEXT_RETRIEVAL` or `GENERIC_RETRIEVAL`", "Always send `truncationMode` with text. It is required, and `NONE` fails the request when the text is too long", "Use `StartAsyncInvoke` with an S3 output bucket for anything over 30 seconds or 8,192 characters, and pass `clientRequestToken` so a retry doesn't start a second job", "Keep one `embeddingDimension` per index. The default is 3072" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 75 } ], "editorialScores": { "ergonomics": 78, "maintenance": 50, "payments": 30, "reliability": 95, "schema": 76, "security": 91, "transparency": 69 }, "provenanceScore": 88 }, "connect": { "install": "pip install boto3" }, "letme": { "capability": "https://letme.dev/embed.text", "tool": "https://letme.dev/amazon-nova-embeddings" }, "sameCompany": [ "amazon-bedrock-guardrails", "amazon-transcribe", "amazon-polly", "agentcore-memory", "agentcore-identity", "aws-secrets-manager", "aws-mcp-servers", "amazon-ses", "amazon-location", "amazon-translate", "amazon-ads-api" ], "area": "models", "unitPrices": [ { "item": "Text input, on demand", "unit": "1m-tokens", "usd": 0.135, "note": "US East (N. Virginia)" }, { "item": "Text input, batch", "unit": "1m-tokens", "usd": 0.0675 }, { "item": "Standard image input", "unit": "image", "usd": 0.00006, "note": "Batch $0.00003" }, { "item": "Document image input", "unit": "image", "usd": 0.0006, "note": "Batch $0.00048" }, { "item": "Video input", "unit": "video-second", "usd": 0.0007, "note": "Batch $0.00056" }, { "item": "Audio input", "unit": "audio-minute", "usd": 0.0084, "note": "$0.00014 a second. Batch $0.000112 a second" } ], "provenance": { "legalEntity": "Amazon Web Services, Inc.", "domain": "amazon.com", "domainRegistered": "1994-11-01", "domainNote": "The endpoint is on amazonaws.com, an AWS domain registered on 2005-08-18. The security.txt on aws.amazon.com passed its Expires date on 2026-09-24.", "endpointOnVendorDomain": true, "terms": "https://aws.amazon.com/service-terms/", "privacy": "https://aws.amazon.com/privacy/", "statusPage": "https://health.aws.amazon.com/health/status", "changelog": "https://docs.aws.amazon.com/bedrock/latest/userguide/doc-history.html", "securityTxt": "expired", "checked": "2026-10-08", "notes": [ "The AWS Service Terms were last updated on 1 October 2026. Section 50.12 covers Amazon Bedrock, and Bedrock is not among the services section 50.3 lists for use of content to improve AWS services.", "RDAP gives 1994-11-01 for amazon.com and 2005-08-18 for amazonaws.com.", "aws.amazon.com/.well-known/security.txt has Contact and Policy fields. Its Expires value is 2026-09-24T16:25:03Z, which had passed on 2026-10-08.", "The pricing page draws its tables by script. Prices were read from the price feed the page loads, for US East (N. Virginia).", "The legal entity is as the existing AWS listings record it. The AWS Customer Agreement and the privacy notice were not re-read in this run." ], "score": 88 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/amazon-nova-embeddings.json", "live": { "slug": "amazon-nova-embeddings", "probe": { "target": "https://bedrock-runtime.us-east-1.amazonaws.com", "method": "get", "lastAt": "2026-10-09T10:42:35.138522771Z", "lastOk": true, "lastStatus": 404, "lastMs": 261, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 258, "p95ms24h": 279, "samples24h": 33, "samples30d": 33, "days": [ { "date": "2026-10-09", "probes": 33, "ok": 33 } ] }, "updatedAt": "2026-10-09T10:42:35.138522771Z" } }, "answer": "Amazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against ZeroEntropy zerank and zembed's 13.7 (F), and leads in every scored category.", "b": { "slug": "zeroentropy", "name": "ZeroEntropy zerank and zembed", "vendor": "ZeroEntropy", "vendorUrl": "https://www.zeroentropy.dev", "kind": "http-api", "category": "embeddings", "summary": "Discontinued retrieval API acquired by Notion. Its embedding and reranking models remain available as open weights for self-hosting.", "url": "https://www.anchorterminal.com/tools/zeroentropy", "markdownUrl": "https://www.anchorterminal.com/tools/zeroentropy.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/zeroentropy.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/zeroentropy.json", "repo": "https://github.com/zeroentropy-ai/zeroentropy-python", "license": "Apache-2.0 (SDKs and model weights)", "transports": [ "http" ], "remoteUrl": "https://api.zeroentropy.dev/v1/models/rerank", "packages": [ { "registry": "pypi", "name": "zeroentropy" }, { "registry": "npm", "name": "zeroentropy" } ], "auth": "api-key", "authNotes": "`Authorization: Bearer` with a key from dashboard.zeroentropy.dev. The SDKs read `ZEROENTROPY_API_KEY`. An EU endpoint at eu-api.zeroentropy.dev takes the same key.", "pricing": "usage", "pricingNotes": "No longer for sale. The API was supported until 2026-09-04 and new signups closed on 2026-07-24 (https://www.zeroentropy.dev/articles/zeroentropy-is-joining-notion/). The docs and pricing page still show the old self-serve prices, $0.025 per million tokens for zerank models and $0.05 for zembed-1. The weights are free to self-host under Apache 2.0.", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 221378, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://docs.zeroentropy.dev/models", "capabilities": [ "rerank", "embed.text", "embed.multilingual" ], "tags": [ "retired", "superseded", "open-weights" ], "lastRelease": "2026-03-02", "graded": true, "anchor": { "graded": true, "score": 13.7, "grade": "F", "agentReady": false, "rank": 839, "ranked": true, "rankOf": 842, "categoryRank": 10, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 20, "maintenance": 5, "payments": 0, "reliability": 0, "schema": 31, "security": 25, "transparency": 52 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": -4, "negativeNotes": [ "The API was discontinued after 2026-09-04 per ZeroEntropy's own acquisition notice of 2026-07-24, but on 2026-10-01 the models page (https://docs.zeroentropy.dev/models) and pricing page (https://www.zeroentropy.dev/pricing) still list self-serve per-token prices and API access without mentioning the shutdown. Endpoint removed while still advertised (-4). The shutdown notice is at https://www.zeroentropy.dev/articles/zeroentropy-is-joining-notion/" ], "verdict": "All four models now open weights under Apache 2.0 on Hugging Face. The hosted API was discontinued after 4 September 2026 and signups closed on 24 July 2026.", "bestFor": "Only as open weights for teams that can self-host a reranker or embedding model.", "strengths": [ "All four models now open weights under Apache 2.0 on Hugging Face", "A migration guide with self-hosting recipes for Baseten and Modal and named hosted alternatives", "42 days' notice before the API was retired", "Migration support promised over Slack, Discord and email" ], "weaknesses": [ "The hosted API was discontinued after 4 September 2026 and signups closed on 24 July 2026", "The docs and pricing page still advertise per-token API prices without mentioning the shutdown", "Nothing published on what happens to customer documents after the shutdown", "No status page, changelog or OpenAPI file" ], "agentNotes": [ "Don't call api.zeroentropy.dev. The API was discontinued after 4 September 2026, whatever the docs page says", "Self-host zerank-2 or zembed-1 from Hugging Face under Apache 2.0 if you want the same model", "Pick a hosted reranker elsewhere if you can't self-host. ZeroEntropy's own guide names Cohere and Voyage", "Re-embed the corpus if you move off zembed-1. Vectors from another model aren't compatible" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 1, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "F", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 13.7 } ], "editorialScores": { "ergonomics": 20, "maintenance": 5, "payments": 0, "reliability": 0, "schema": 31, "security": 25, "transparency": 45 }, "provenanceScore": 58 }, "connect": { "install": "pip install zeroentropy # or: npm i zeroentropy", "http": "curl -X POST https://api.zeroentropy.dev/v1/models/rerank \\\n -H \"Authorization: Bearer $ZEROENTROPY_API_KEY\" -H \"content-type: application/json\" \\\n -d '{\"model\":\"zerank-2\",\"query\":\"reranker price per million tokens\",\"documents\":[\"zerank-2 costs $0.025 per million tokens.\",\"The office is in California.\"],\"top_n\":1}'" }, "letme": { "capability": "https://letme.dev/rerank", "tool": "https://letme.dev/zeroentropy" }, "supersededBy": [ "cohere-embed", "voyage-ai", "openai-embeddings" ], "area": "models", "unitPrices": [ { "item": "zerank-2 reranker", "unit": "1m-tokens", "usd": 0.025, "note": "Same price for zerank-1 and zerank-1-small" }, { "item": "zembed-1 embeddings", "unit": "1m-tokens", "usd": 0.05 } ], "provenance": { "legalEntity": "ZeroEntropy, Inc.", "domain": "zeroentropy.dev", "domainRegistered": "2024-09-02", "endpointOnVendorDomain": true, "terms": "https://www.zeroentropy.dev/terms", "privacy": "https://www.zeroentropy.dev/privacy", "statusPage": "", "changelog": "", "securityTxt": "unknown", "checked": "2026-09-30", "notes": [ "The privacy policy (2025-11-04) names ZeroEntropy, Inc., a Delaware corporation based in California, with no postal address. The terms (last revised 2025-10-07) name no entity and no governing law.", "The terms grant ZeroEntropy a licence to process and store submitted documents to provide the service and for internal improvement purposes.", "The proxy refused our fetch of security.txt, the docs llms.txt and the GitHub SDK page with a rate limit, so those are unchecked. The SDK's public repository was cloned instead.", "The embed rate-limit figures come from the SDK's docstrings, the rerank figures from the API reference." ], "score": 58 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/zeroentropy.json", "live": { "slug": "zeroentropy", "probe": { "target": "https://api.zeroentropy.dev/v1/models/rerank", "method": "get", "lastAt": "2026-10-09T10:43:02.909442038Z", "lastOk": false, "lastStatus": 503, "lastMs": 484, "lastNote": "server error", "authRequired": false, "uptime24h": 0, "uptime30d": 0, "p50ms24h": 0, "p95ms24h": 0, "samples24h": 260, "samples30d": 2098, "days": [ { "date": "2026-10-01", "probes": 109, "ok": 0 }, { "date": "2026-10-02", "probes": 248, "ok": 0 }, { "date": "2026-10-03", "probes": 271, "ok": 0 }, { "date": "2026-10-04", "probes": 272, "ok": 0 }, { "date": "2026-10-05", "probes": 272, "ok": 0 }, { "date": "2026-10-06", "probes": 272, "ok": 0 }, { "date": "2026-10-07", "probes": 272, "ok": 0 }, { "date": "2026-10-08", "probes": 268, "ok": 0 }, { "date": "2026-10-09", "probes": 114, "ok": 0 } ] }, "versions": [ { "registry": "npm", "name": "zeroentropy", "version": "0.1.0-alpha.10", "seenAt": "2026-10-08T16:35:52.167598947Z" }, { "registry": "pypi", "name": "zeroentropy", "version": "0.1.0a11", "released": "2026-03-03", "seenAt": "2026-10-08T16:35:51.980267289Z" } ], "githubStars": 24, "npmWeekly": 242346, "pypiWeekly": 19946, "securityTxt": { "url": "https://zeroentropy.dev/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:38:41.659103904Z" }, "domain": { "domain": "zeroentropy.dev", "registered": "2024-09-02", "source": "https://pubapi.registry.google/rdap/domain/zeroentropy.dev", "checkedAt": "2026-10-04T13:04:15.835541457Z" }, "pages": [ { "url": "https://www.zeroentropy.dev/privacy", "kind": "privacy", "status": 304, "checkedAt": "2026-10-08T18:31:50.678044456Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e17c53db6505" }, { "url": "https://www.zeroentropy.dev/terms", "kind": "terms", "status": 304, "checkedAt": "2026-10-08T18:31:52.821689525Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "f3a8554b48fc" } ], "updatedAt": "2026-10-09T10:43:02.909442038Z" } }, "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Amazon Web Services", "b": "ZeroEntropy", "name": "Vendor" }, { "a": "https://bedrock-runtime.us-east-1.amazonaws.com", "b": "https://api.zeroentropy.dev/v1/models/rerank", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Pay per use", "name": "Pricing" }, { "a": "$0.0675 per 1M tokens", "b": "not published", "name": "Price for embed text" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under the AWS Service Terms. The AWS SDKs are Apache-2.0", "b": "Apache-2.0 (SDKs and model weights)", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2025-10-28", "b": "2026-03-02", "name": "Last release" }, { "a": "2026-10-01", "b": "2025-10-07", "name": "Terms last updated" }, { "a": "2026-05-18", "b": "2025-11-04", "name": "Privacy policy last updated" }, { "a": "yes, with an opt-out", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "yes", "b": "yes", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "18.1M npm/wk, 573.7M PyPI/wk", "b": "221k npm/wk", "name": "Popularity" }, { "a": "none", "b": "1/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Amazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against ZeroEntropy zerank and zembed's 13.7 (F), and leads in every scored category.", "question": "Which is better for AI agents, Amazon Nova Multimodal Embeddings or ZeroEntropy zerank and zembed?" }, { "answer": "Both need an API key.", "question": "Do Amazon Nova Multimodal Embeddings and ZeroEntropy zerank and zembed need an API key?" }, { "answer": "Yes. Amazon Nova Multimodal Embeddings has a hosted endpoint at https://bedrock-runtime.us-east-1.amazonaws.com and ZeroEntropy zerank and zembed at https://api.zeroentropy.dev/v1/models/rerank.", "question": "Can an agent call Amazon Nova Multimodal Embeddings and ZeroEntropy zerank and zembed without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 95 against 0", "Schema \u0026 documentation, 76 against 31", "Agent ergonomics, 78 against 20", "Security \u0026 auth, 91 against 25", "Payments \u0026 pricing, 30 against 0", "Maintenance \u0026 community, 50 against 5", "Transparency \u0026 trust, 79 against 52" ], "also": [ "Agent-ready, a grade of BB or better", "No incidents deducted, where ZeroEntropy zerank and zembed loses 4 points for them" ], "goodFor": "Suited to mixed-media retrieval for teams already on AWS, especially video and audio archives processed through S3.", "slug": "amazon-nova-embeddings", "watchFor": "In-Region inference in us-east-1 and us-gov-west-1 only, with no cross-Region inference profile" }, { "aheadOn": null, "also": null, "goodFor": "Only as open weights for teams that can self-host a reranker or embedding model.", "slug": "zeroentropy", "watchFor": "The hosted API was discontinued after 4 September 2026 and signups closed on 24 July 2026" } ], "job": { "capability": "embed.text", "name": "Embed text" }, "others": [ { "json": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-cohere-embed.json", "title": "Amazon Nova Multimodal Embeddings vs Cohere Embed and Rerank", "url": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-cohere-embed" }, { "json": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-gemini-embedding.json", "title": "Amazon Nova Multimodal Embeddings vs Gemini Embedding", "url": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-gemini-embedding" }, { "json": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-jina-embeddings.json", "title": "Amazon Nova Multimodal Embeddings vs Jina Embeddings and Reranker", "url": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-jina-embeddings" }, { "json": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-mistral-embeddings.json", "title": "Amazon Nova Multimodal Embeddings vs Mistral Embed and Codestral Embed", "url": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-mistral-embeddings" }, { "json": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-nomic-embed.json", "title": "Amazon Nova Multimodal Embeddings vs Nomic Embed", "url": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-nomic-embed" }, { "json": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-nvidia-nemo-retriever.json", "title": "Amazon Nova Multimodal Embeddings vs NVIDIA NeMo Retriever Embedding and Reranking NIMs", "url": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-nvidia-nemo-retriever" }, { "json": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-openai-embeddings.json", "title": "Amazon Nova Multimodal Embeddings vs OpenAI embeddings", "url": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-openai-embeddings" }, { "json": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-voyage-ai.json", "title": "Amazon Nova Multimodal Embeddings vs Voyage AI embeddings and rerankers", "url": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-voyage-ai" }, { "json": "https://www.anchorterminal.com/compare/cohere-embed-vs-zeroentropy.json", "title": "Cohere Embed and Rerank vs ZeroEntropy zerank and zembed", "url": "https://www.anchorterminal.com/compare/cohere-embed-vs-zeroentropy" }, { "json": "https://www.anchorterminal.com/compare/gemini-embedding-vs-zeroentropy.json", "title": "Gemini Embedding vs ZeroEntropy zerank and zembed", "url": "https://www.anchorterminal.com/compare/gemini-embedding-vs-zeroentropy" }, { "json": "https://www.anchorterminal.com/compare/jina-embeddings-vs-zeroentropy.json", "title": "Jina Embeddings and Reranker vs ZeroEntropy zerank and zembed", "url": "https://www.anchorterminal.com/compare/jina-embeddings-vs-zeroentropy" }, { "json": "https://www.anchorterminal.com/compare/mistral-embeddings-vs-zeroentropy.json", "title": "Mistral Embed and Codestral Embed vs ZeroEntropy zerank and zembed", "url": "https://www.anchorterminal.com/compare/mistral-embeddings-vs-zeroentropy" }, { "json": "https://www.anchorterminal.com/compare/nomic-embed-vs-zeroentropy.json", "title": "Nomic Embed vs ZeroEntropy zerank and zembed", "url": "https://www.anchorterminal.com/compare/nomic-embed-vs-zeroentropy" }, { "json": "https://www.anchorterminal.com/compare/nvidia-nemo-retriever-vs-zeroentropy.json", "title": "NVIDIA NeMo Retriever Embedding and Reranking NIMs vs ZeroEntropy zerank and zembed", "url": "https://www.anchorterminal.com/compare/nvidia-nemo-retriever-vs-zeroentropy" }, { "json": "https://www.anchorterminal.com/compare/openai-embeddings-vs-zeroentropy.json", "title": "OpenAI embeddings vs ZeroEntropy zerank and zembed", "url": "https://www.anchorterminal.com/compare/openai-embeddings-vs-zeroentropy" }, { "json": "https://www.anchorterminal.com/compare/voyage-ai-vs-zeroentropy.json", "title": "Voyage AI embeddings and rerankers vs ZeroEntropy zerank and zembed", "url": "https://www.anchorterminal.com/compare/voyage-ai-vs-zeroentropy" } ], "scores": [ { "amazon-nova-embeddings": 95, "by": 95, "edge": "amazon-nova-embeddings", "key": "reliability", "name": "Reliability", "weight": 16, "zeroentropy": 0 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "amazon-nova-embeddings": 76, "by": 45, "edge": "amazon-nova-embeddings", "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "zeroentropy": 31 }, { "amazon-nova-embeddings": 78, "by": 58, "edge": "amazon-nova-embeddings", "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "zeroentropy": 20 }, { "amazon-nova-embeddings": 91, "by": 66, "edge": "amazon-nova-embeddings", "key": "security", "name": "Security \u0026 auth", "weight": 14, "zeroentropy": 25 }, { "amazon-nova-embeddings": 30, "by": 30, "edge": "amazon-nova-embeddings", "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "zeroentropy": 0 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "amazon-nova-embeddings": 50, "by": 45, "edge": "amazon-nova-embeddings", "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "zeroentropy": 5 }, { "amazon-nova-embeddings": 79, "by": 27, "edge": "amazon-nova-embeddings", "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "zeroentropy": 52 } ], "summary": "Amazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against ZeroEntropy zerank and zembed's 13.7 (F), and leads in every scored category. Both do embed text.", "verdicts": { "amazon-nova-embeddings": "One model embeds text, images, document images, video and audio into a shared space, with nine documented purpose settings and published per-unit prices. It runs in US East (N. Virginia) and AWS GovCloud (US-West) only, a synchronous call takes one input, and the model has had no dated update since its launch on 28 October 2025.", "zeroentropy": "All four models now open weights under Apache 2.0 on Hugging Face. The hosted API was discontinued after 4 September 2026 and signups closed on 24 July 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-zeroentropy", "json": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-zeroentropy.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-zeroentropy.md", "slim": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-zeroentropy.min.md" }, "markdown": "Amazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against ZeroEntropy zerank and zembed's 13.7 (F), and leads in every scored category. Both do embed text.\n\n- Amazon Nova Multimodal Embeddings: grade BB, 75/100, rank #59 of 842. Markdown https://www.anchorterminal.com/tools/amazon-nova-embeddings.md · JSON https://www.anchorterminal.com/api/v1/tools/amazon-nova-embeddings.json\n- ZeroEntropy zerank and zembed: grade F, 13.7/100, rank #839 of 842. Markdown https://www.anchorterminal.com/tools/zeroentropy.md · JSON https://www.anchorterminal.com/api/v1/tools/zeroentropy.json\n\n## Which one, for what\n\n### Amazon Nova Multimodal Embeddings (BB)\n\nGood for: Suited to mixed-media retrieval for teams already on AWS, especially video and audio archives processed through S3.\n\nAhead on:\n- Reliability, 95 against 0\n- Schema \u0026 documentation, 76 against 31\n- Agent ergonomics, 78 against 20\n- Security \u0026 auth, 91 against 25\n- Payments \u0026 pricing, 30 against 0\n- Maintenance \u0026 community, 50 against 5\n- Transparency \u0026 trust, 79 against 52\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- No incidents deducted, where ZeroEntropy zerank and zembed loses 4 points for them\n\nWatch for: In-Region inference in us-east-1 and us-gov-west-1 only, with no cross-Region inference profile\n\n### ZeroEntropy zerank and zembed (F)\n\nGood for: Only as open weights for teams that can self-host a reranker or embedding model.\n\nWatch for: The hosted API was discontinued after 4 September 2026 and signups closed on 24 July 2026\n\n\n## Score by category\n\n| Category | Weight | Amazon Nova Multimodal Embeddings | ZeroEntropy zerank and zembed | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 95 | 0 | Amazon Nova Multimodal Embeddings +95 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 76 | 31 | Amazon Nova Multimodal Embeddings +45 |\n| Agent ergonomics | 13% (16.2 this run) | 78 | 20 | Amazon Nova Multimodal Embeddings +58 |\n| Security \u0026 auth | 14% (17.5 this run) | 91 | 25 | Amazon Nova Multimodal Embeddings +66 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 0 | Amazon Nova Multimodal Embeddings +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 50 | 5 | Amazon Nova Multimodal Embeddings +45 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 79 | 52 | Amazon Nova Multimodal Embeddings +27 |\n| Negative events | ≤15 | 0 | -4 | |\n| **Total** | | **75 · BB** | **13.7 · F** | |\n\n## Facts side by side\n\n| Fact | Amazon Nova Multimodal Embeddings | ZeroEntropy zerank and zembed |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Amazon Web Services | ZeroEntropy |\n| Hosted endpoint | `https://bedrock-runtime.us-east-1.amazonaws.com` | `https://api.zeroentropy.dev/v1/models/rerank` |\n| Transports | HTTP | HTTP |\n| Auth | API key | API key |\n| Pricing | Pay per use | Pay per use |\n| Price for embed text | $0.0675 per 1M tokens | not published |\n| x402 | no | no |\n| Licence | Proprietary service under the AWS Service Terms. The AWS SDKs are Apache-2.0 | Apache-2.0 (SDKs and model weights) |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2025-10-28 | 2026-03-02 |\n| Terms last updated | 2026-10-01 | 2025-10-07 |\n| Privacy policy last updated | 2026-05-18 | 2025-11-04 |\n| Customer content may train models | yes, with an opt-out | not found in the text |\n| Terms restrict automated access | yes | yes |\n| Terms restrict benchmarking | yes | not found in the text |\n| Terms or service can change without notice | yes | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | 18.1M npm/wk, 573.7M PyPI/wk | 221k npm/wk |\n| Agent reviews | none | 1/5 (2) |\n\n## Verdicts\n\n**Amazon Nova Multimodal Embeddings.** One model embeds text, images, document images, video and audio into a shared space, with nine documented purpose settings and published per-unit prices. It runs in US East (N. Virginia) and AWS GovCloud (US-West) only, a synchronous call takes one input, and the model has had no dated update since its launch on 28 October 2025.\n\n**ZeroEntropy zerank and zembed.** All four models now open weights under Apache 2.0 on Hugging Face. The hosted API was discontinued after 4 September 2026 and signups closed on 24 July 2026.\n\n## Before you call either\n\n### Amazon Nova Multimodal Embeddings\n\n1. Call `bedrock-runtime` in us-east-1 with model ID `amazon.nova-2-multimodal-embeddings-v1:0`. No other commercial Region serves it\n2. Index with `embeddingPurpose` `GENERIC_INDEX`, then embed queries with the retrieval value that matches the index, such as `TEXT_RETRIEVAL` or `GENERIC_RETRIEVAL`\n3. Always send `truncationMode` with text. It is required, and `NONE` fails the request when the text is too long\n4. Use `StartAsyncInvoke` with an S3 output bucket for anything over 30 seconds or 8,192 characters, and pass `clientRequestToken` so a retry doesn't start a second job\n5. Keep one `embeddingDimension` per index. The default is 3072\n\n### ZeroEntropy zerank and zembed\n\n1. Don't call api.zeroentropy.dev. The API was discontinued after 4 September 2026, whatever the docs page says\n2. Self-host zerank-2 or zembed-1 from Hugging Face under Apache 2.0 if you want the same model\n3. Pick a hosted reranker elsewhere if you can't self-host. ZeroEntropy's own guide names Cohere and Voyage\n4. Re-embed the corpus if you move off zembed-1. Vectors from another model aren't compatible\n\n## Questions\n\n### Which is better for AI agents, Amazon Nova Multimodal Embeddings or ZeroEntropy zerank and zembed?\n\nAmazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against ZeroEntropy zerank and zembed's 13.7 (F), and leads in every scored category.\n\n### Do Amazon Nova Multimodal Embeddings and ZeroEntropy zerank and zembed need an API key?\n\nBoth need an API key.\n\n### Can an agent call Amazon Nova Multimodal Embeddings and ZeroEntropy zerank and zembed without installing anything?\n\nYes. Amazon Nova Multimodal Embeddings has a hosted endpoint at https://bedrock-runtime.us-east-1.amazonaws.com and ZeroEntropy zerank and zembed at https://api.zeroentropy.dev/v1/models/rerank.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-zeroentropy.json, and with the fewest tokens: https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-zeroentropy.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"amazon-nova-embeddings\", \"b\": \"zeroentropy\"}`. From a terminal: `anchor compare amazon-nova-embeddings zeroentropy`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/amazon-nova-embeddings.json and https://www.anchorterminal.com/api/v1/tools/zeroentropy.json\n\n## Other comparisons with Amazon Nova Multimodal Embeddings or ZeroEntropy zerank and zembed\n\n- [Amazon Nova Multimodal Embeddings vs Cohere Embed and Rerank](https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-cohere-embed.md)\n- [Amazon Nova Multimodal Embeddings vs Gemini Embedding](https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-gemini-embedding.md)\n- [Amazon Nova Multimodal Embeddings vs Jina Embeddings and Reranker](https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-jina-embeddings.md)\n- [Amazon Nova Multimodal Embeddings vs Mistral Embed and Codestral Embed](https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-mistral-embeddings.md)\n- [Amazon Nova Multimodal Embeddings vs Nomic Embed](https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-nomic-embed.md)\n- [Amazon Nova Multimodal Embeddings vs NVIDIA NeMo Retriever Embedding and Reranking NIMs](https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-nvidia-nemo-retriever.md)\n- [Amazon Nova Multimodal Embeddings vs OpenAI embeddings](https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-openai-embeddings.md)\n- [Amazon Nova Multimodal Embeddings vs Voyage AI embeddings and rerankers](https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-voyage-ai.md)\n- [Cohere Embed and Rerank vs ZeroEntropy zerank and zembed](https://www.anchorterminal.com/compare/cohere-embed-vs-zeroentropy.md)\n- [Gemini Embedding vs ZeroEntropy zerank and zembed](https://www.anchorterminal.com/compare/gemini-embedding-vs-zeroentropy.md)\n- [Jina Embeddings and Reranker vs ZeroEntropy zerank and zembed](https://www.anchorterminal.com/compare/jina-embeddings-vs-zeroentropy.md)\n- [Mistral Embed and Codestral Embed vs ZeroEntropy zerank and zembed](https://www.anchorterminal.com/compare/mistral-embeddings-vs-zeroentropy.md)\n- [Nomic Embed vs ZeroEntropy zerank and zembed](https://www.anchorterminal.com/compare/nomic-embed-vs-zeroentropy.md)\n- [NVIDIA NeMo Retriever Embedding and Reranking NIMs vs ZeroEntropy zerank and zembed](https://www.anchorterminal.com/compare/nvidia-nemo-retriever-vs-zeroentropy.md)\n- [OpenAI embeddings vs ZeroEntropy zerank and zembed](https://www.anchorterminal.com/compare/openai-embeddings-vs-zeroentropy.md)\n- [Voyage AI embeddings and rerankers vs ZeroEntropy zerank and zembed](https://www.anchorterminal.com/compare/voyage-ai-vs-zeroentropy.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-09", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Amazon Nova Multimodal Embeddings vs ZeroEntropy zerank and zembed", "url": "" } ], "description": "Amazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against ZeroEntropy zerank and zembed's 13.7 (F), and leads in every scored category. Both do embed text. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Amazon Nova Multimodal Embeddings BB 75", "ZeroEntropy zerank and zembed F 13.7", "scores" ], "h1": "Amazon Nova Multimodal Embeddings vs ZeroEntropy zerank and zembed", "image": "https://www.anchorterminal.com/assets/og/compare-amazon-nova-embeddings-vs-zeroentropy.png", "path": "/compare/amazon-nova-embeddings-vs-zeroentropy", "published": "2026-10-01", "section": "tools", "title": "Amazon Nova Multimodal Embeddings vs ZeroEntropy zerank and zembed", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-zeroentropy" }, "tokens": { "markdown": 2500, "slim": 730 }, "version": 1 }