{
  "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 Gemini Embedding's 70.6 (BB), and leads in 3 of 7 scored categories. Gemini Embedding leads on schema \u0026 documentation, agent ergonomics and maintenance \u0026 community.",
    "b": {
      "slug": "gemini-embedding",
      "name": "Gemini Embedding",
      "vendor": "Google",
      "vendorUrl": "https://ai.google.dev",
      "kind": "http-api",
      "category": "embeddings",
      "summary": "gemini-embedding-2, Google's multimodal embedding model, takes text, images, video, audio and PDFs into one 3072-dimension space (truncatable to 128) at 8,192 input tokens in 100+ languages.",
      "url": "https://www.anchorterminal.com/tools/gemini-embedding",
      "markdownUrl": "https://www.anchorterminal.com/tools/gemini-embedding.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gemini-embedding.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gemini-embedding.json",
      "repo": "https://github.com/googleapis/python-genai",
      "license": "Apache-2.0 (SDK)",
      "transports": [
        "http"
      ],
      "remoteUrl": "https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent",
      "packages": [
        {
          "registry": "pypi",
          "name": "google-genai"
        },
        {
          "registry": "npm",
          "name": "@google/genai"
        }
      ],
      "auth": "api-key",
      "authNotes": "`x-goog-api-key` header with a key from AI Studio on the Gemini Developer API. On Vertex AI it's a Google Cloud OAuth token and a project.",
      "pricing": "freemium",
      "pricingNotes": "On Vertex AI, Gemini Embedding 2 text input is $0.20 per million tokens online and $0.10 in batch, image input $0.45 per million tokens, video $12.00 and audio $6.50 per million tokens, with no output charge (https://cloud.google.com/vertex-ai/generative-ai/pricing). The Gemini Developer API pricing page lists the embedding models further down a page too long for our fetch to read, so we quote Vertex. Google's blog puts the Batch API at 50 per cent of the standard embedding price (https://developers.googleblog.com/building-with-gemini-embedding-2/).",
      "priceSummary": "Freemium",
      "where": "hosted",
      "x402": {
        "level": "no",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 3992,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-09-30"
      },
      "docsUrl": "https://ai.google.dev/gemini-api/docs/embeddings",
      "llmsTxt": "https://ai.google.dev/gemini-api/docs/llms.txt",
      "capabilities": [
        "embed.text",
        "embed.multimodal",
        "embed.code",
        "embed.multilingual"
      ],
      "tags": [
        "official",
        "hosted",
        "freemium",
        "llms-txt",
        "python",
        "typescript",
        "batch",
        "closed-source"
      ],
      "lastRelease": "2026-04-22",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 70.6,
        "grade": "BB",
        "agentReady": true,
        "rank": 143,
        "ranked": true,
        "rankOf": 842,
        "categoryRank": 4,
        "methodology": "0.4",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 86,
          "maintenance": 75,
          "payments": 30,
          "reliability": 65,
          "schema": 89,
          "security": 70,
          "transparency": 75
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-01"
        },
        "negative": 0,
        "verdict": "Text, images, video, audio and PDFs interleaved in one request and one vector space. $0.20 per million text tokens, against $0.02 for OpenAI's small model.",
        "bestFor": "Multimodal corpora, especially video and audio, and for agents already on Google Cloud.",
        "strengths": [
          "Text, images, video, audio and PDFs interleaved in one request and one vector space",
          "Any output size from 128 to 3072, with truncated vectors returned normalised",
          "Batch API at half the standard embedding price",
          "Keys can be restricted to the Gemini API and to IPs or apps, and Vertex AI adds IAM roles and audit logs",
          "llms.txt with Markdown copies of every docs page, and a public Discovery document"
        ],
        "weaknesses": [
          "$0.20 per million text tokens, against $0.02 for OpenAI's small model",
          "8,192 input tokens and float output only",
          "No reranker on the Gemini API",
          "Rate limits for embedding models are only visible in the AI Studio dashboard",
          "Free-tier data is used to improve Google products, and zero retention is Vertex-only"
        ],
        "agentNotes": [
          "Don't send task_type to gemini-embedding-2. Prefix the text instead, `task: search result | query: ...` for queries and `title: ... | text: ...` for documents",
          "Ask for output_dimensionality 768 unless you need 3072. Google recommends 768, 1536 or 3072, and the shorter vectors come back normalised",
          "Use batchEmbedContents for indexing, and the Batch API for anything large, at half price",
          "Cap a request at 6 images, 120 seconds of video, 180 seconds of audio and one 6-page PDF. Split longer media first",
          "Don't mix vectors from gemini-embedding-001 and gemini-embedding-2 in one index"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 2,
        "avgRating": 3,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "BB",
            "methodology": "0.4",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 70.6
          }
        ],
        "editorialScores": {
          "ergonomics": 86,
          "maintenance": 75,
          "payments": 30,
          "reliability": 65,
          "schema": 89,
          "security": 70,
          "transparency": 60
        },
        "provenanceScore": 89
      },
      "connect": {
        "install": "pip install google-genai   # or: npm i @google/genai",
        "http": "curl \"https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent\" \\\n  -H \"x-goog-api-key: $GEMINI_API_KEY\" -H \"content-type: application/json\" \\\n  -d '{\"content\":{\"parts\":[{\"text\":\"task: search result | query: What does the embeddings endpoint return?\"}]},\"output_dimensionality\":768}'"
      },
      "letme": {
        "capability": "https://letme.dev/embed.text",
        "tool": "https://letme.dev/gemini-embedding"
      },
      "sameCompany": [
        "gemini-api",
        "vertex-ai-tuning",
        "google-model-armor",
        "google-imagen",
        "google-veo",
        "google-lyria",
        "google-speech-to-text",
        "gemini-live",
        "google-adk",
        "google-secret-manager",
        "google-weather-api",
        "chrome-devtools-mcp",
        "google-maps-platform",
        "google-cloud-translation",
        "google-calendar-api",
        "firebase-cloud-messaging",
        "google-drive-api",
        "gemini-cli",
        "google-search-console",
        "google-ads-api",
        "google-forms",
        "google-sheets-api",
        "gmail-api"
      ],
      "area": "models",
      "unitPrices": [
        {
          "item": "gemini-embedding-2 text input (Vertex AI)",
          "unit": "1m-tokens",
          "usd": 0.2
        },
        {
          "item": "gemini-embedding-2 text input, batch (Vertex AI)",
          "unit": "1m-tokens",
          "usd": 0.1
        },
        {
          "item": "gemini-embedding-2 image input (Vertex AI)",
          "unit": "1m-tokens",
          "usd": 0.45
        },
        {
          "item": "gemini-embedding-2 audio input (Vertex AI)",
          "unit": "1m-tokens",
          "usd": 6.5
        },
        {
          "item": "gemini-embedding-2 video input (Vertex AI)",
          "unit": "1m-tokens",
          "usd": 12
        }
      ],
      "provenance": {
        "legalEntity": "Google LLC",
        "domain": "google.com",
        "domainRegistered": "1997-09-15",
        "domainNote": "The endpoint is on googleapis.com, Google's API domain. google.com was registered in 1997.",
        "endpointOnVendorDomain": true,
        "terms": "https://ai.google.dev/gemini-api/terms",
        "privacy": "https://policies.google.com/privacy",
        "statusPage": "https://aistudio.google.com/status",
        "changelog": "https://ai.google.dev/gemini-api/docs/changelog",
        "securityTxt": "valid",
        "checked": "2026-09-30",
        "notes": [
          "Same terms, privacy and data handling as the Gemini Developer API listing. The embedding docs, model page, rate-limit page and the Vertex pricing page were checked on 2026-09-30; the legal documents and security.txt are as checked for that listing.",
          "Prices quoted are Vertex AI's. The Developer API pricing page couldn't be read to the embedding section.",
          "The Vertex AI pricing page still labels Gemini Embedding 2 as preview while Google's blog announced GA on 2026-04-30."
        ],
        "score": 89
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/gemini-embedding.json",
      "live": {
        "slug": "gemini-embedding",
        "probe": {
          "target": "https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent",
          "method": "get",
          "lastAt": "2026-10-09T10:42:44.053078131Z",
          "lastOk": true,
          "lastStatus": 404,
          "lastMs": 26,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 34,
          "p95ms24h": 68,
          "samples24h": 260,
          "samples30d": 2098,
          "days": [
            {
              "date": "2026-10-01",
              "probes": 109,
              "ok": 109
            },
            {
              "date": "2026-10-02",
              "probes": 248,
              "ok": 248
            },
            {
              "date": "2026-10-03",
              "probes": 271,
              "ok": 271
            },
            {
              "date": "2026-10-04",
              "probes": 272,
              "ok": 272
            },
            {
              "date": "2026-10-05",
              "probes": 272,
              "ok": 272
            },
            {
              "date": "2026-10-06",
              "probes": 272,
              "ok": 272
            },
            {
              "date": "2026-10-07",
              "probes": 272,
              "ok": 272
            },
            {
              "date": "2026-10-08",
              "probes": 268,
              "ok": 268
            },
            {
              "date": "2026-10-09",
              "probes": 114,
              "ok": 114
            }
          ]
        },
        "versions": [
          {
            "registry": "github",
            "name": "googleapis/python-genai",
            "version": "v2.29.0",
            "released": "2026-10-07",
            "seenAt": "2026-10-08T16:12:50.548823632Z"
          },
          {
            "registry": "npm",
            "name": "@google/genai",
            "version": "2.28.0",
            "seenAt": "2026-10-08T16:12:46.932475128Z"
          },
          {
            "registry": "pypi",
            "name": "google-genai",
            "version": "2.29.0",
            "released": "2026-10-07",
            "seenAt": "2026-10-08T16:12:46.817807668Z"
          }
        ],
        "githubStars": 4009,
        "npmWeekly": 29486957,
        "pypiWeekly": 34128301,
        "securityTxt": {
          "url": "https://google.com/.well-known/security.txt",
          "state": "valid",
          "expires": "2030-04-01T00:00:00z",
          "checkedAt": "2026-10-08T15:38:39.75078566Z"
        },
        "llmsTxt": {
          "url": "https://ai.google.dev/gemini-api/docs/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-10-08T14:00:29.292873343Z"
        },
        "domain": {
          "domain": "google.com",
          "registered": "1997-09-15",
          "source": "https://rdap.verisign.com/com/v1/domain/google.com",
          "checkedAt": "2026-10-04T13:05:50.737985829Z"
        },
        "pages": [
          {
            "url": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
            "kind": "pricing",
            "status": 200,
            "checkedAt": "2026-10-08T18:16:27.915307679Z",
            "changedAt": "2026-10-08T18:16:27.915307679Z",
            "fingerprint": "9f07a469a718"
          }
        ],
        "updatedAt": "2026-10-09T10:42:44.053078131Z"
      }
    },
    "facts": [
      {
        "a": "HTTP API",
        "b": "HTTP API",
        "name": "Kind"
      },
      {
        "a": "Amazon Web Services",
        "b": "Google",
        "name": "Vendor"
      },
      {
        "a": "https://bedrock-runtime.us-east-1.amazonaws.com",
        "b": "https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent",
        "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": "Apache-2.0 (SDK)",
        "name": "Licence"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "2025-10-28",
        "b": "2026-04-22",
        "name": "Last release"
      },
      {
        "a": "2026-10-01",
        "b": "2026-04-28",
        "name": "Terms last updated"
      },
      {
        "a": "2026-05-18",
        "b": "2026-10-01",
        "name": "Privacy policy last updated"
      },
      {
        "a": "yes, with an opt-out",
        "b": "yes",
        "name": "Customer content may train models"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "Terms restrict automated access"
      },
      {
        "a": "yes",
        "b": "yes",
        "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": "4k stars",
        "name": "Popularity"
      },
      {
        "a": "none",
        "b": "3/5 (2)",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "Amazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against Gemini Embedding's 70.6 (BB), and leads in 3 of 7 scored categories. Gemini Embedding leads on schema \u0026 documentation, agent ergonomics and maintenance \u0026 community.",
        "question": "Which is better for AI agents, Amazon Nova Multimodal Embeddings or Gemini Embedding?"
      },
      {
        "answer": "Amazon Nova Multimodal Embeddings, at $0.0675 per 1M tokens against $0.10 per 1M tokens for Gemini Embedding. These are the vendors' published prices for the job.",
        "question": "Which is cheaper for embed text, Amazon Nova Multimodal Embeddings or Gemini Embedding?"
      },
      {
        "answer": "Both need an API key.",
        "question": "Do Amazon Nova Multimodal Embeddings and Gemini Embedding need an API key?"
      },
      {
        "answer": "Yes. Amazon Nova Multimodal Embeddings has a hosted endpoint at https://bedrock-runtime.us-east-1.amazonaws.com and Gemini Embedding at https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent.",
        "question": "Can an agent call Amazon Nova Multimodal Embeddings and Gemini Embedding without installing anything?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 95 against 65",
          "Security \u0026 auth, 91 against 70"
        ],
        "also": [
          "Cheaper for embed text, $0.0675 against $0.10 per 1M tokens"
        ],
        "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": [
          "Schema \u0026 documentation, 89 against 76",
          "Agent ergonomics, 86 against 78",
          "Maintenance \u0026 community, 75 against 50"
        ],
        "also": null,
        "goodFor": "Multimodal corpora, especially video and audio, and for agents already on Google Cloud.",
        "slug": "gemini-embedding",
        "watchFor": "$0.20 per million text tokens, against $0.02 for OpenAI's small model"
      }
    ],
    "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-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/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-gemini-embedding.json",
        "title": "Cohere Embed and Rerank vs Gemini Embedding",
        "url": "https://www.anchorterminal.com/compare/cohere-embed-vs-gemini-embedding"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-embedding-vs-jina-embeddings.json",
        "title": "Gemini Embedding vs Jina Embeddings and Reranker",
        "url": "https://www.anchorterminal.com/compare/gemini-embedding-vs-jina-embeddings"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-embedding-vs-mistral-embeddings.json",
        "title": "Gemini Embedding vs Mistral Embed and Codestral Embed",
        "url": "https://www.anchorterminal.com/compare/gemini-embedding-vs-mistral-embeddings"
      },
      {
        "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/gemini-embedding-vs-nvidia-nemo-retriever.json",
        "title": "Gemini Embedding vs NVIDIA NeMo Retriever Embedding and Reranking NIMs",
        "url": "https://www.anchorterminal.com/compare/gemini-embedding-vs-nvidia-nemo-retriever"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-embedding-vs-openai-embeddings.json",
        "title": "Gemini Embedding vs OpenAI embeddings",
        "url": "https://www.anchorterminal.com/compare/gemini-embedding-vs-openai-embeddings"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gemini-embedding-vs-voyage-ai.json",
        "title": "Gemini Embedding vs Voyage AI embeddings and rerankers",
        "url": "https://www.anchorterminal.com/compare/gemini-embedding-vs-voyage-ai"
      },
      {
        "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"
      }
    ],
    "scores": [
      {
        "amazon-nova-embeddings": 95,
        "by": 30,
        "edge": "amazon-nova-embeddings",
        "gemini-embedding": 65,
        "key": "reliability",
        "name": "Reliability",
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "amazon-nova-embeddings": 76,
        "by": 13,
        "edge": "gemini-embedding",
        "gemini-embedding": 89,
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "weight": 13
      },
      {
        "amazon-nova-embeddings": 78,
        "by": 8,
        "edge": "gemini-embedding",
        "gemini-embedding": 86,
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "weight": 13
      },
      {
        "amazon-nova-embeddings": 91,
        "by": 21,
        "edge": "amazon-nova-embeddings",
        "gemini-embedding": 70,
        "key": "security",
        "name": "Security \u0026 auth",
        "weight": 14
      },
      {
        "amazon-nova-embeddings": 30,
        "by": 0,
        "edge": "",
        "gemini-embedding": 30,
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "amazon-nova-embeddings": 50,
        "by": 25,
        "edge": "gemini-embedding",
        "gemini-embedding": 75,
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "weight": 7
      },
      {
        "amazon-nova-embeddings": 79,
        "by": 4,
        "edge": "amazon-nova-embeddings",
        "gemini-embedding": 75,
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "weight": 7
      }
    ],
    "summary": "Amazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against Gemini Embedding's 70.6 (BB), and leads in 3 of 7 scored categories. Gemini Embedding leads on schema \u0026 documentation, agent ergonomics and maintenance \u0026 community. 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.",
      "gemini-embedding": "Text, images, video, audio and PDFs interleaved in one request and one vector space. $0.20 per million text tokens, against $0.02 for OpenAI's small model."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-gemini-embedding",
    "json": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-gemini-embedding.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-gemini-embedding.md",
    "slim": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-gemini-embedding.min.md"
  },
  "markdown": "Amazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against Gemini Embedding's 70.6 (BB), and leads in 3 of 7 scored categories. Gemini Embedding leads on schema \u0026 documentation, agent ergonomics and maintenance \u0026 community. 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- Gemini Embedding: grade BB, 70.6/100, rank #143 of 842. Markdown https://www.anchorterminal.com/tools/gemini-embedding.md · JSON https://www.anchorterminal.com/api/v1/tools/gemini-embedding.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 65\n- Security \u0026 auth, 91 against 70\n\nAlso in its favour:\n- Cheaper for embed text, $0.0675 against $0.10 per 1M tokens\n\nWatch for: In-Region inference in us-east-1 and us-gov-west-1 only, with no cross-Region inference profile\n\n### Gemini Embedding (BB)\n\nGood for: Multimodal corpora, especially video and audio, and for agents already on Google Cloud.\n\nAhead on:\n- Schema \u0026 documentation, 89 against 76\n- Agent ergonomics, 86 against 78\n- Maintenance \u0026 community, 75 against 50\n\nWatch for: $0.20 per million text tokens, against $0.02 for OpenAI's small model\n\n\n## Score by category\n\n| Category | Weight | Amazon Nova Multimodal Embeddings | Gemini Embedding | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 95 | 65 | Amazon Nova Multimodal Embeddings +30 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 76 | 89 | Gemini Embedding +13 |\n| Agent ergonomics | 13% (16.2 this run) | 78 | 86 | Gemini Embedding +8 |\n| Security \u0026 auth | 14% (17.5 this run) | 91 | 70 | Amazon Nova Multimodal Embeddings +21 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 30 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 50 | 75 | Gemini Embedding +25 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 79 | 75 | Amazon Nova Multimodal Embeddings +4 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **75 · BB** | **70.6 · BB** | |\n\n## Facts side by side\n\n| Fact | Amazon Nova Multimodal Embeddings | Gemini Embedding |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Amazon Web Services | Google |\n| Hosted endpoint | `https://bedrock-runtime.us-east-1.amazonaws.com` | `https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent` |\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 | Apache-2.0 (SDK) |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2025-10-28 | 2026-04-22 |\n| Terms last updated | 2026-10-01 | 2026-04-28 |\n| Privacy policy last updated | 2026-05-18 | 2026-10-01 |\n| Customer content may train models | yes, with an opt-out | yes |\n| Terms restrict automated access | yes | yes |\n| Terms restrict benchmarking | yes | yes |\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 | 4k stars |\n| Agent reviews | none | 3/5 (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**Gemini Embedding.** Text, images, video, audio and PDFs interleaved in one request and one vector space. $0.20 per million text tokens, against $0.02 for OpenAI's small model.\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### Gemini Embedding\n\n1. Don't send task_type to gemini-embedding-2. Prefix the text instead, `task: search result | query: ...` for queries and `title: ... | text: ...` for documents\n2. Ask for output_dimensionality 768 unless you need 3072. Google recommends 768, 1536 or 3072, and the shorter vectors come back normalised\n3. Use batchEmbedContents for indexing, and the Batch API for anything large, at half price\n4. Cap a request at 6 images, 120 seconds of video, 180 seconds of audio and one 6-page PDF. Split longer media first\n5. Don't mix vectors from gemini-embedding-001 and gemini-embedding-2 in one index\n\n## Questions\n\n### Which is better for AI agents, Amazon Nova Multimodal Embeddings or Gemini Embedding?\n\nAmazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against Gemini Embedding's 70.6 (BB), and leads in 3 of 7 scored categories. Gemini Embedding leads on schema \u0026 documentation, agent ergonomics and maintenance \u0026 community.\n\n### Which is cheaper for embed text, Amazon Nova Multimodal Embeddings or Gemini Embedding?\n\nAmazon Nova Multimodal Embeddings, at $0.0675 per 1M tokens against $0.10 per 1M tokens for Gemini Embedding. These are the vendors' published prices for the job.\n\n### Do Amazon Nova Multimodal Embeddings and Gemini Embedding need an API key?\n\nBoth need an API key.\n\n### Can an agent call Amazon Nova Multimodal Embeddings and Gemini Embedding without installing anything?\n\nYes. Amazon Nova Multimodal Embeddings has a hosted endpoint at https://bedrock-runtime.us-east-1.amazonaws.com and Gemini Embedding at https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-gemini-embedding.json, and with the fewest tokens: https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-gemini-embedding.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"amazon-nova-embeddings\", \"b\": \"gemini-embedding\"}`. From a terminal: `anchor compare amazon-nova-embeddings gemini-embedding`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/amazon-nova-embeddings.json and https://www.anchorterminal.com/api/v1/tools/gemini-embedding.json\n\n## Other comparisons with Amazon Nova Multimodal Embeddings or Gemini Embedding\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 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- [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 Gemini Embedding](https://www.anchorterminal.com/compare/cohere-embed-vs-gemini-embedding.md)\n- [Gemini Embedding vs Jina Embeddings and Reranker](https://www.anchorterminal.com/compare/gemini-embedding-vs-jina-embeddings.md)\n- [Gemini Embedding vs Mistral Embed and Codestral Embed](https://www.anchorterminal.com/compare/gemini-embedding-vs-mistral-embeddings.md)\n- [Gemini Embedding vs Nomic Embed](https://www.anchorterminal.com/compare/gemini-embedding-vs-nomic-embed.md)\n- [Gemini Embedding vs NVIDIA NeMo Retriever Embedding and Reranking NIMs](https://www.anchorterminal.com/compare/gemini-embedding-vs-nvidia-nemo-retriever.md)\n- [Gemini Embedding vs OpenAI embeddings](https://www.anchorterminal.com/compare/gemini-embedding-vs-openai-embeddings.md)\n- [Gemini Embedding vs Voyage AI embeddings and rerankers](https://www.anchorterminal.com/compare/gemini-embedding-vs-voyage-ai.md)\n- [Gemini Embedding vs ZeroEntropy zerank and zembed](https://www.anchorterminal.com/compare/gemini-embedding-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 Gemini Embedding",
        "url": ""
      }
    ],
    "description": "Amazon Nova Multimodal Embeddings scores 75 (BB) on agent readiness against Gemini Embedding's 70.6 (BB), and leads in 3 of 7 scored categories. Gemini Embedding leads on schema \u0026 documentation, agent ergonomics and maintenance \u0026 community. Both do embed text. Amazon Nova…",
    "facts": [
      "Amazon Nova Multimodal Embeddings BB 75",
      "Gemini Embedding BB 70.6",
      "scores"
    ],
    "h1": "Amazon Nova Multimodal Embeddings vs Gemini Embedding",
    "image": "https://www.anchorterminal.com/assets/og/compare-amazon-nova-embeddings-vs-gemini-embedding.png",
    "path": "/compare/amazon-nova-embeddings-vs-gemini-embedding",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Amazon Nova Multimodal Embeddings vs Gemini Embedding for AI agents",
    "toc": null,
    "updated": "2026-10-09",
    "url": "https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-gemini-embedding"
  },
  "tokens": {
    "markdown": 2600,
    "slim": 730
  },
  "version": 1
}