{
  "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": "2026-10-09T11:46:21.229746191Z",
          "lastOk": true,
          "lastStatus": 404,
          "lastMs": 249,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 256,
          "p95ms24h": 279,
          "samples24h": 44,
          "samples30d": 44,
          "days": [
            {
              "date": "2026-10-09",
              "probes": 44,
              "ok": 44
            }
          ]
        },
        "updatedAt": "2026-10-09T11:46:21.229746191Z"
      }
    },
    "answer": "Amazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against Nomic Embed's 49.2 (D), and leads in every scored category.",
    "b": {
      "slug": "nomic-embed",
      "name": "Nomic Embed",
      "vendor": "Nomic, Inc.",
      "vendorUrl": "https://www.nomic.ai",
      "kind": "http-api",
      "category": "embeddings",
      "summary": "Nomic's hosted embedding endpoints on the Atlas API turn text and images into vectors with the open-weight Nomic Embed models. Agents call them over HTTP with an API key or through the Python and TypeScript clients.",
      "url": "https://www.anchorterminal.com/tools/nomic-embed",
      "markdownUrl": "https://www.anchorterminal.com/tools/nomic-embed.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/nomic-embed.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/nomic-embed.json",
      "repo": "https://github.com/nomic-ai/nomic",
      "license": "Proprietary hosted API. Model weights Apache-2.0 on Hugging Face. The Python client declares Apache in setup.py and the TypeScript client is MIT",
      "transports": [
        "http"
      ],
      "remoteUrl": "https://api-atlas.nomic.ai/v1/embedding/text",
      "packages": [
        {
          "registry": "pypi",
          "name": "nomic"
        },
        {
          "registry": "npm",
          "name": "@nomic-ai/atlas"
        }
      ],
      "auth": "api-key",
      "authNotes": "`Authorization: Bearer` with a Nomic API key created in the Atlas dashboard at atlas.nomic.ai/data. Keys are tied to a user and billed to the organisation, and can be scoped to an organisation, a dataset or a user. The clients also accept a refresh token. Sign-up is in a browser, and we couldn't confirm that new accounts are still accepted (https://docs.nomic.ai/api/getting-started/getting-started).",
      "pricing": "freemium",
      "pricingNotes": "No rendered public page prices the embedding endpoint. www.nomic.ai/pricing lists only the Nomic Platform plans (Free, Individual at $20 a month, Business at $40 a user a month). The Atlas web app's script lists a starter plan with 10M tokens free and paid plans at $1 per 10M tokens with 10M or 100M included a month, and images at $1 per 50,000. We couldn't render that page or confirm whether a card is needed (checked 2026-10-08).",
      "priceSummary": "Freemium",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the API reference, the OpenAPI document or the pricing pages (checked 2026-10-08).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 1881,
        "npmWeekly": 8551,
        "pypiWeekly": 3833,
        "asOf": "2026-10-08"
      },
      "docsUrl": "https://docs.nomic.ai/reference/api/embed-text-v-1-embedding-text-post",
      "openapi": "https://api-atlas.nomic.ai/v1/api-reference/openapi.json",
      "capabilities": [
        "embed.text",
        "embed.multimodal",
        "embed.multilingual",
        "embed.code"
      ],
      "tags": [
        "hosted",
        "freemium",
        "api-key",
        "openapi",
        "open-weights",
        "python",
        "typescript"
      ],
      "lastRelease": "2025-11-11",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 49.2,
        "grade": "D",
        "agentReady": false,
        "rank": 711,
        "ranked": true,
        "rankOf": 842,
        "categoryRank": 9,
        "methodology": "0.4",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 69,
          "maintenance": 28,
          "payments": 20,
          "reliability": 38,
          "schema": 65,
          "security": 62,
          "transparency": 46
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-08"
        },
        "negative": 0,
        "verdict": "The text models have Apache-2.0 weights and a public OpenAPI 3.1 contract, so vectors made through the hosted endpoint can be reproduced locally. Nomic's current site and documentation index describe a construction-industry product, no rendered public page prices the endpoint, and no published terms or status component name it.",
        "bestFor": "Teams that want a hosted endpoint for an open-weight model they can also run themselves, with the same vectors either way.",
        "strengths": [
          "Weights for nomic-embed-text-v1, v1.5, v2-moe, nomic-embed-code and nomic-embed-vision-v1.5 are Apache-2.0 on Hugging Face",
          "Public OpenAPI 3.1 document for the Atlas API (v0.57.0) with typed request and response schemas for both embedding endpoints",
          "nomic-embed-text-v1.5 accepts a dimensionality from 64 to 768, and inputs up to 8,192 tokens per text",
          "The Python client retries 429 and 5xx responses with exponential backoff and can run the same model locally with inference_mode set to local",
          "API keys can be scoped to an organisation, a dataset or a user, per the Atlas access-control page"
        ],
        "weaknesses": [
          "docs.nomic.ai/llms.txt and www.nomic.ai now describe a product for architecture, engineering and construction firms, and the documentation index no longer lists the embedding pages",
          "No rendered public page states a price for the endpoint. The $1 per 10M tokens figure comes from the Atlas web app's script",
          "status.nomic.ai has no component for api-atlas.nomic.ai, and no SLA was found",
          "The published terms and privacy policy cover the Nomic Platform at app.nomic.ai and don't name Atlas or the embedding API",
          "The Python client's last release was 3.9.0 on 11 November 2025, and the API reference documents only a 422 error"
        ],
        "agentNotes": [
          "Set task_type to search_query for queries and search_document for stored text. The default is search_document",
          "Name the model in every request. The API defaults to nomic-embed-text-v1, while the Python client defaults to nomic-embed-text-v1.5",
          "Keep under 1,200 requests per five minutes per IP address. The Python client sends at most 10 texts a request",
          "Set long_text_mode to truncate or mean. Texts over 8,192 tokens are averaged across chunks by default on the API",
          "Pass dimensionality only with nomic-embed-text-v1.5, between 64 and 768"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "D",
            "methodology": "0.4",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 49.2
          }
        ],
        "editorialScores": {
          "ergonomics": 69,
          "maintenance": 28,
          "payments": 20,
          "reliability": 38,
          "schema": 65,
          "security": 62,
          "transparency": 47
        },
        "provenanceScore": 45
      },
      "connect": {
        "install": "pip install nomic",
        "http": "curl -X POST https://api-atlas.nomic.ai/v1/embedding/text \\\n  -H \"Authorization: Bearer $NOMIC_API_KEY\" -H \"Content-Type: application/json\" \\\n  -d '{\"texts\":[\"The text you want to embed.\"],\"model\":\"nomic-embed-text-v1.5\",\"task_type\":\"search_document\"}'"
      },
      "letme": {
        "capability": "https://letme.dev/embed.text",
        "tool": "https://letme.dev/nomic-embed"
      },
      "sameCompany": [
        "gpt4all"
      ],
      "area": "models",
      "unitPrices": [
        {
          "item": "Text embedding tokens beyond the plan's monthly allowance",
          "unit": "1m-tokens",
          "usd": 0.1,
          "note": "$1 per 10M tokens, read from the Atlas web app's script, not a rendered pricing page"
        }
      ],
      "provenance": {
        "legalEntity": "Nomic, Inc.",
        "domain": "nomic.ai",
        "domainRegistered": "",
        "endpointOnVendorDomain": true,
        "terms": "",
        "privacy": "",
        "statusPage": "",
        "changelog": "https://github.com/nomic-ai/nomic/blob/main/CHANGELOG.md",
        "securityTxt": "none",
        "checked": "2026-10-08",
        "notes": [
          "terms and privacy are left out. Nomic publishes Terms of Service for Business and Enterprise accounts (20 April 2026), Individual Terms of Service for Free and Individual accounts (25 August 2026) and a privacy policy (15 January 2026) that covers www.nomic.ai and the platform at app.nomic.ai. None names Atlas, atlas.nomic.ai or the embedding API (https://www.nomic.ai/legal.json).",
          "Both sets of terms name Nomic, Inc., a Delaware corporation, under Delaware law.",
          "status.nomic.ai lists the Nomic Platform in four regions (drive.nomic.ai, au, eu and uk), each with a Nomic API and a Platform Web Service component. It has no component for api-atlas.nomic.ai, so statusPage is left empty.",
          "www.nomic.ai, docs.nomic.ai and api-atlas.nomic.ai each return 404 for /.well-known/security.txt. The security page gives security@nomic.ai for vulnerability reports.",
          "The changelog is the Python client's. No changelog for the Atlas API was found."
        ],
        "score": 45
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/nomic-embed.json",
      "live": {
        "slug": "nomic-embed",
        "probe": {
          "target": "https://api-atlas.nomic.ai/v1/embedding/text",
          "method": "get",
          "lastAt": "2026-10-09T11:46:35.260805738Z",
          "lastOk": true,
          "lastStatus": 405,
          "lastMs": 448,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 431,
          "p95ms24h": 479,
          "samples24h": 195,
          "samples30d": 195,
          "days": [
            {
              "date": "2026-10-08",
              "probes": 70,
              "ok": 70
            },
            {
              "date": "2026-10-09",
              "probes": 125,
              "ok": 125
            }
          ]
        },
        "pages": [
          {
            "url": "https://raw.githubusercontent.com/nomic-ai/nomic/main/CHANGELOG.md",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-10-08T18:24:31.732147651Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "5cd028b474d0"
          }
        ],
        "updatedAt": "2026-10-09T11:46:35.260805738Z"
      }
    },
    "facts": [
      {
        "a": "HTTP API",
        "b": "HTTP API",
        "name": "Kind"
      },
      {
        "a": "Amazon Web Services",
        "b": "Nomic, Inc.",
        "name": "Vendor"
      },
      {
        "a": "https://bedrock-runtime.us-east-1.amazonaws.com",
        "b": "https://api-atlas.nomic.ai/v1/embedding/text",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP",
        "b": "HTTP",
        "name": "Transports"
      },
      {
        "a": "API key",
        "b": "API key",
        "name": "Auth"
      },
      {
        "a": "Pay per use",
        "b": "Freemium",
        "name": "Pricing"
      },
      {
        "a": "$0.0675 per 1M tokens",
        "b": "$0.10 per 1M tokens",
        "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": "Proprietary hosted API. Model weights Apache-2.0 on Hugging Face. The Python client declares Apache in setup.py and the TypeScript client is MIT",
        "name": "Licence"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "no",
        "name": "llms.txt"
      },
      {
        "a": "2025-10-28",
        "b": "2025-11-11",
        "name": "Last release"
      },
      {
        "a": "2026-10-01",
        "b": "no document linked",
        "name": "Terms last updated"
      },
      {
        "a": "2026-05-18",
        "b": "no document linked",
        "name": "Privacy policy last updated"
      },
      {
        "a": "yes, with an opt-out",
        "b": "",
        "name": "Customer content may train models"
      },
      {
        "a": "yes",
        "b": "",
        "name": "Terms restrict automated access"
      },
      {
        "a": "yes",
        "b": "",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "yes",
        "b": "",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "not found in the text",
        "b": "",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "18.1M npm/wk, 573.7M PyPI/wk",
        "b": "1.9k stars, 8.6k npm/wk, 3.8k PyPI/wk",
        "name": "Popularity"
      }
    ],
    "faq": [
      {
        "answer": "Amazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against Nomic Embed's 49.2 (D), and leads in every scored category.",
        "question": "Which is better for AI agents, Amazon Nova Multimodal Embeddings or Nomic Embed?"
      },
      {
        "answer": "Amazon Nova Multimodal Embeddings, at $0.0675 per 1M tokens against $0.10 per 1M tokens for Nomic Embed. These are the vendors' published prices for the job.",
        "question": "Which is cheaper for embed text, Amazon Nova Multimodal Embeddings or Nomic Embed?"
      },
      {
        "answer": "Both need an API key.",
        "question": "Do Amazon Nova Multimodal Embeddings and Nomic Embed need an API key?"
      },
      {
        "answer": "Yes. Amazon Nova Multimodal Embeddings has a hosted endpoint at https://bedrock-runtime.us-east-1.amazonaws.com and Nomic Embed at https://api-atlas.nomic.ai/v1/embedding/text.",
        "question": "Can an agent call Amazon Nova Multimodal Embeddings and Nomic Embed without installing anything?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 95 against 38",
          "Schema \u0026 documentation, 76 against 65",
          "Agent ergonomics, 78 against 69",
          "Security \u0026 auth, 91 against 62",
          "Payments \u0026 pricing, 30 against 20",
          "Maintenance \u0026 community, 50 against 28",
          "Transparency \u0026 trust, 79 against 46"
        ],
        "also": [
          "Cheaper for embed text, $0.0675 against $0.10 per 1M tokens",
          "Agent-ready, a grade of BB or better"
        ],
        "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": "Teams that want a hosted endpoint for an open-weight model they can also run themselves, with the same vectors either way.",
        "slug": "nomic-embed",
        "watchFor": "docs.nomic.ai/llms.txt and www.nomic.ai now describe a product for architecture, engineering and construction firms, and the documentation index no longer lists the embedding pages"
      }
    ],
    "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-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/amazon-nova-embeddings-vs-zeroentropy.json",
        "title": "Amazon Nova Multimodal Embeddings vs ZeroEntropy zerank and zembed",
        "url": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-zeroentropy"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cohere-embed-vs-nomic-embed.json",
        "title": "Cohere Embed and Rerank vs Nomic Embed",
        "url": "https://www.anchorterminal.com/compare/cohere-embed-vs-nomic-embed"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-embedding-vs-nomic-embed.json",
        "title": "Gemini Embedding vs Nomic Embed",
        "url": "https://www.anchorterminal.com/compare/gemini-embedding-vs-nomic-embed"
      },
      {
        "json": "https://www.anchorterminal.com/compare/jina-embeddings-vs-nomic-embed.json",
        "title": "Jina Embeddings and Reranker vs Nomic Embed",
        "url": "https://www.anchorterminal.com/compare/jina-embeddings-vs-nomic-embed"
      },
      {
        "json": "https://www.anchorterminal.com/compare/mistral-embeddings-vs-nomic-embed.json",
        "title": "Mistral Embed and Codestral Embed vs Nomic Embed",
        "url": "https://www.anchorterminal.com/compare/mistral-embeddings-vs-nomic-embed"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nomic-embed-vs-nvidia-nemo-retriever.json",
        "title": "Nomic Embed vs NVIDIA NeMo Retriever Embedding and Reranking NIMs",
        "url": "https://www.anchorterminal.com/compare/nomic-embed-vs-nvidia-nemo-retriever"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nomic-embed-vs-openai-embeddings.json",
        "title": "Nomic Embed vs OpenAI embeddings",
        "url": "https://www.anchorterminal.com/compare/nomic-embed-vs-openai-embeddings"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nomic-embed-vs-voyage-ai.json",
        "title": "Nomic Embed vs Voyage AI embeddings and rerankers",
        "url": "https://www.anchorterminal.com/compare/nomic-embed-vs-voyage-ai"
      },
      {
        "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"
      }
    ],
    "scores": [
      {
        "amazon-nova-embeddings": 95,
        "by": 57,
        "edge": "amazon-nova-embeddings",
        "key": "reliability",
        "name": "Reliability",
        "nomic-embed": 38,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "amazon-nova-embeddings": 76,
        "by": 11,
        "edge": "amazon-nova-embeddings",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "nomic-embed": 65,
        "weight": 13
      },
      {
        "amazon-nova-embeddings": 78,
        "by": 9,
        "edge": "amazon-nova-embeddings",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "nomic-embed": 69,
        "weight": 13
      },
      {
        "amazon-nova-embeddings": 91,
        "by": 29,
        "edge": "amazon-nova-embeddings",
        "key": "security",
        "name": "Security \u0026 auth",
        "nomic-embed": 62,
        "weight": 14
      },
      {
        "amazon-nova-embeddings": 30,
        "by": 10,
        "edge": "amazon-nova-embeddings",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "nomic-embed": 20,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "amazon-nova-embeddings": 50,
        "by": 22,
        "edge": "amazon-nova-embeddings",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "nomic-embed": 28,
        "weight": 7
      },
      {
        "amazon-nova-embeddings": 79,
        "by": 33,
        "edge": "amazon-nova-embeddings",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "nomic-embed": 46,
        "weight": 7
      }
    ],
    "summary": "Amazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against Nomic Embed's 49.2 (D), and leads in every scored category. Both do embed text. Amazon Nova Multimodal Embeddings is cheaper for embed text, $0.0675 against $0.10 per 1M tokens.",
    "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.",
      "nomic-embed": "The text models have Apache-2.0 weights and a public OpenAPI 3.1 contract, so vectors made through the hosted endpoint can be reproduced locally. Nomic's current site and documentation index describe a construction-industry product, no rendered public page prices the endpoint, and no published terms or status component name it."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-nomic-embed",
    "json": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-nomic-embed.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-nomic-embed.md",
    "slim": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-nomic-embed.min.md"
  },
  "markdown": "Amazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against Nomic Embed's 49.2 (D), and leads in every scored category. Both do embed text. Amazon Nova Multimodal Embeddings is cheaper for embed text, $0.0675 against $0.10 per 1M tokens.\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- Nomic Embed: grade D, 49.2/100, rank #711 of 842. Markdown https://www.anchorterminal.com/tools/nomic-embed.md · JSON https://www.anchorterminal.com/api/v1/tools/nomic-embed.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 38\n- Schema \u0026 documentation, 76 against 65\n- Agent ergonomics, 78 against 69\n- Security \u0026 auth, 91 against 62\n- Payments \u0026 pricing, 30 against 20\n- Maintenance \u0026 community, 50 against 28\n- Transparency \u0026 trust, 79 against 46\n\nAlso in its favour:\n- Cheaper for embed text, $0.0675 against $0.10 per 1M tokens\n- Agent-ready, a grade of BB or better\n\nWatch for: In-Region inference in us-east-1 and us-gov-west-1 only, with no cross-Region inference profile\n\n### Nomic Embed (D)\n\nGood for: Teams that want a hosted endpoint for an open-weight model they can also run themselves, with the same vectors either way.\n\nWatch for: docs.nomic.ai/llms.txt and www.nomic.ai now describe a product for architecture, engineering and construction firms, and the documentation index no longer lists the embedding pages\n\n\n## Score by category\n\n| Category | Weight | Amazon Nova Multimodal Embeddings | Nomic Embed | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 95 | 38 | Amazon Nova Multimodal Embeddings +57 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 76 | 65 | Amazon Nova Multimodal Embeddings +11 |\n| Agent ergonomics | 13% (16.2 this run) | 78 | 69 | Amazon Nova Multimodal Embeddings +9 |\n| Security \u0026 auth | 14% (17.5 this run) | 91 | 62 | Amazon Nova Multimodal Embeddings +29 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 20 | Amazon Nova Multimodal Embeddings +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 50 | 28 | Amazon Nova Multimodal Embeddings +22 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 79 | 46 | Amazon Nova Multimodal Embeddings +33 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **75 · BB** | **49.2 · D** | |\n\n## Facts side by side\n\n| Fact | Amazon Nova Multimodal Embeddings | Nomic Embed |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Amazon Web Services | Nomic, Inc. |\n| Hosted endpoint | `https://bedrock-runtime.us-east-1.amazonaws.com` | `https://api-atlas.nomic.ai/v1/embedding/text` |\n| Transports | HTTP | HTTP |\n| Auth | API key | API key |\n| Pricing | Pay per use | Freemium |\n| Price for embed text | $0.0675 per 1M tokens | $0.10 per 1M tokens |\n| x402 | no | no |\n| Licence | Proprietary service under the AWS Service Terms. The AWS SDKs are Apache-2.0 | Proprietary hosted API. Model weights Apache-2.0 on Hugging Face. The Python client declares Apache in setup.py and the TypeScript client is MIT |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2025-10-28 | 2025-11-11 |\n| Terms last updated | 2026-10-01 | no document linked |\n| Privacy policy last updated | 2026-05-18 | no document linked |\n| Customer content may train models | yes, with an opt-out |  |\n| Terms restrict automated access | yes |  |\n| Terms restrict benchmarking | yes |  |\n| Terms or service can change without notice | yes |  |\n| Arbitration or class-action waiver | not found in the text |  |\n| Popularity | 18.1M npm/wk, 573.7M PyPI/wk | 1.9k stars, 8.6k npm/wk, 3.8k PyPI/wk |\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**Nomic Embed.** The text models have Apache-2.0 weights and a public OpenAPI 3.1 contract, so vectors made through the hosted endpoint can be reproduced locally. Nomic's current site and documentation index describe a construction-industry product, no rendered public page prices the endpoint, and no published terms or status component name it.\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### Nomic Embed\n\n1. Set task_type to search_query for queries and search_document for stored text. The default is search_document\n2. Name the model in every request. The API defaults to nomic-embed-text-v1, while the Python client defaults to nomic-embed-text-v1.5\n3. Keep under 1,200 requests per five minutes per IP address. The Python client sends at most 10 texts a request\n4. Set long_text_mode to truncate or mean. Texts over 8,192 tokens are averaged across chunks by default on the API\n5. Pass dimensionality only with nomic-embed-text-v1.5, between 64 and 768\n\n## Questions\n\n### Which is better for AI agents, Amazon Nova Multimodal Embeddings or Nomic Embed?\n\nAmazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against Nomic Embed's 49.2 (D), and leads in every scored category.\n\n### Which is cheaper for embed text, Amazon Nova Multimodal Embeddings or Nomic Embed?\n\nAmazon Nova Multimodal Embeddings, at $0.0675 per 1M tokens against $0.10 per 1M tokens for Nomic Embed. These are the vendors' published prices for the job.\n\n### Do Amazon Nova Multimodal Embeddings and Nomic Embed need an API key?\n\nBoth need an API key.\n\n### Can an agent call Amazon Nova Multimodal Embeddings and Nomic Embed without installing anything?\n\nYes. Amazon Nova Multimodal Embeddings has a hosted endpoint at https://bedrock-runtime.us-east-1.amazonaws.com and Nomic Embed at https://api-atlas.nomic.ai/v1/embedding/text.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-nomic-embed.json, and with the fewest tokens: https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-nomic-embed.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"amazon-nova-embeddings\", \"b\": \"nomic-embed\"}`. From a terminal: `anchor compare amazon-nova-embeddings nomic-embed`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/amazon-nova-embeddings.json and https://www.anchorterminal.com/api/v1/tools/nomic-embed.json\n\n## Other comparisons with Amazon Nova Multimodal Embeddings or Nomic Embed\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 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- [Amazon Nova Multimodal Embeddings vs ZeroEntropy zerank and zembed](https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-zeroentropy.md)\n- [Cohere Embed and Rerank vs Nomic Embed](https://www.anchorterminal.com/compare/cohere-embed-vs-nomic-embed.md)\n- [Gemini Embedding vs Nomic Embed](https://www.anchorterminal.com/compare/gemini-embedding-vs-nomic-embed.md)\n- [Jina Embeddings and Reranker vs Nomic Embed](https://www.anchorterminal.com/compare/jina-embeddings-vs-nomic-embed.md)\n- [Mistral Embed and Codestral Embed vs Nomic Embed](https://www.anchorterminal.com/compare/mistral-embeddings-vs-nomic-embed.md)\n- [Nomic Embed vs NVIDIA NeMo Retriever Embedding and Reranking NIMs](https://www.anchorterminal.com/compare/nomic-embed-vs-nvidia-nemo-retriever.md)\n- [Nomic Embed vs OpenAI embeddings](https://www.anchorterminal.com/compare/nomic-embed-vs-openai-embeddings.md)\n- [Nomic Embed vs Voyage AI embeddings and rerankers](https://www.anchorterminal.com/compare/nomic-embed-vs-voyage-ai.md)\n- [Nomic Embed vs ZeroEntropy zerank and zembed](https://www.anchorterminal.com/compare/nomic-embed-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 Nomic Embed",
        "url": ""
      }
    ],
    "description": "Amazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against Nomic Embed's 49.2 (D), and leads in every scored category. Both do embed text. Amazon Nova Multimodal Embeddings is cheaper for embed text, $0.0675 against $0.10 per 1M tokens. Category scores, facts…",
    "facts": [
      "Amazon Nova Multimodal Embeddings BB 75",
      "Nomic Embed D 49.2",
      "scores"
    ],
    "h1": "Amazon Nova Multimodal Embeddings vs Nomic Embed",
    "image": "https://www.anchorterminal.com/assets/og/compare-amazon-nova-embeddings-vs-nomic-embed.png",
    "path": "/compare/amazon-nova-embeddings-vs-nomic-embed",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Amazon Nova Multimodal Embeddings vs Nomic Embed for AI agents",
    "toc": null,
    "updated": "2026-10-09",
    "url": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-nomic-embed"
  },
  "tokens": {
    "markdown": 2650,
    "slim": 780
  },
  "version": 1
}