{
  "data": {
    "a": {
      "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": 613,
        "ranked": true,
        "rankOf": 722,
        "categoryRank": 7,
        "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": "2026-10-08T20:21:21.371841332Z",
          "lastOk": true,
          "lastStatus": 405,
          "lastMs": 417,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 425,
          "p95ms24h": 467,
          "samples24h": 32,
          "samples30d": 32,
          "days": [
            {
              "date": "2026-10-08",
              "probes": 32,
              "ok": 32
            }
          ]
        },
        "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": "2026-10-08T20:21:21.371841332Z"
      }
    },
    "answer": "OpenAI embeddings scores 73.2 (BB) on agent readiness against Nomic Embed's 49.2 (D), and leads in every scored category.",
    "b": {
      "slug": "openai-embeddings",
      "name": "OpenAI embeddings",
      "vendor": "OpenAI",
      "vendorUrl": "https://developers.openai.com",
      "kind": "http-api",
      "category": "embeddings",
      "summary": "OpenAI's text embedding API, with adjustable output dimensions for search and retrieval applications.",
      "url": "https://www.anchorterminal.com/tools/openai-embeddings",
      "markdownUrl": "https://www.anchorterminal.com/tools/openai-embeddings.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/openai-embeddings.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/openai-embeddings.json",
      "repo": "https://github.com/openai/openai-python",
      "license": "Apache-2.0 (SDK)",
      "transports": [
        "http"
      ],
      "remoteUrl": "https://api.openai.com/v1/embeddings",
      "packages": [
        {
          "registry": "pypi",
          "name": "openai"
        },
        {
          "registry": "npm",
          "name": "openai"
        }
      ],
      "auth": "api-key",
      "authNotes": "`Authorization: Bearer` with a project key from the OpenAI platform. Same key and account as the rest of the OpenAI API.",
      "pricing": "usage",
      "pricingNotes": "text-embedding-3-small $0.02 and text-embedding-3-large $0.13 per million input tokens. No output charge. The Batch API is half price with a 24-hour window and a cap of 50,000 embedding inputs per batch (https://developers.openai.com/api/docs/models/text-embedding-3-large, https://developers.openai.com/api/docs/guides/batch). Prepaid credits, $5 minimum, shared with the rest of the API.",
      "priceSummary": "Pay per use",
      "where": "hosted",
      "x402": {
        "level": "no",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 31300,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-09-30"
      },
      "docsUrl": "https://developers.openai.com/api/docs/guides/embeddings",
      "llmsTxt": "https://developers.openai.com/llms.txt",
      "openapi": "https://github.com/openai/openai-openapi",
      "capabilities": [
        "embed.text",
        "embed.multilingual"
      ],
      "tags": [
        "official",
        "hosted",
        "card-required",
        "openapi",
        "llms-txt",
        "python",
        "typescript",
        "batch",
        "closed-source"
      ],
      "lastRelease": "2024-01-25",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 73.2,
        "grade": "BB",
        "agentReady": true,
        "rank": 79,
        "ranked": true,
        "rankOf": 722,
        "categoryRank": 1,
        "methodology": "0.4",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 90,
          "maintenance": 60,
          "payments": 30,
          "reliability": 65,
          "schema": 89,
          "security": 95,
          "transparency": 85
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "high",
          "date": "2026-10-01"
        },
        "negative": -2,
        "negativeNotes": [
          "A breach at Mixpanel, OpenAI's analytics vendor, began on 2025-11-09 and was reported to OpenAI on 2025-11-25. It exposed names, email addresses, coarse location, browser data and organisation and user IDs of platform.openai.com users, but no API keys, API requests or usage data. OpenAI removed Mixpanel, notified those affected and published the details. Fixed and documented, so a small, decayed deduction (-2). https://openai.com/index/mixpanel-incident/"
        ],
        "verdict": "text-embedding-3-small at $0.02 per million tokens, $0.01 through the Batch API. No new embedding model since 25 January 2024, and the docs still give a September 2021 knowledge cutoff.",
        "bestFor": "An agent already on OpenAI that needs cheap general-purpose text retrieval with a small index.",
        "strengths": [
          "text-embedding-3-small at $0.02 per million tokens, $0.01 through the Batch API",
          "Restricted project keys are set per endpoint, so an agent's key can be cut down to read and model calls",
          "Up to 2,048 inputs and 300,000 tokens in one request",
          "OpenAPI document, llms.txt and a dated changelog shared with the rest of the OpenAI API",
          "No training on API data by default, six months' notice before a GA model is retired"
        ],
        "weaknesses": [
          "No new embedding model since 25 January 2024, and the docs still give a September 2021 knowledge cutoff",
          "Text only, 8,192 tokens an input, and no reranker",
          "Over-long inputs fail rather than being truncated, and output is float or base64 only",
          "A free tier is listed, but credits are prepaid after adding payment details, and nothing confirms a start without a card",
          "Elevated errors across the API including Embeddings on 17 and 29 September 2026, for about 1.5 and 5.4 hours"
        ],
        "agentNotes": [
          "Pack up to 2,048 chunks in one request and keep the request under 300,000 tokens",
          "Count tokens before sending. An input over 8,192 tokens is rejected, not truncated",
          "Pass dimensions 512 or 256 on text-embedding-3-large when the vector store bills by size, and re-normalise any vector you cut yourself",
          "Split a Batch API index job into batches of under 50,000 inputs. It's half price with a 24-hour window",
          "Read Retry-After on a 429 and tell quota errors (add credits) apart from rate limits (wait)"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 2,
        "avgRating": 4.5,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "high",
            "grade": "BB",
            "methodology": "0.4",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 73.2
          }
        ],
        "editorialScores": {
          "ergonomics": 90,
          "maintenance": 60,
          "payments": 30,
          "reliability": 65,
          "schema": 89,
          "security": 95,
          "transparency": 75
        },
        "provenanceScore": 94
      },
      "connect": {
        "install": "pip install openai   # or: npm i openai",
        "http": "curl https://api.openai.com/v1/embeddings \\\n  -H \"Authorization: Bearer $OPENAI_API_KEY\" -H \"content-type: application/json\" \\\n  -d '{\"model\":\"text-embedding-3-small\",\"input\":[\"What does the embeddings endpoint return?\"],\"dimensions\":512}'"
      },
      "letme": {
        "capability": "https://letme.dev/embed.text",
        "tool": "https://letme.dev/openai-embeddings"
      },
      "sameCompany": [
        "openai-api",
        "openai-moderation",
        "openai-image-api",
        "openai-sora",
        "openai-agents-sdk",
        "openai-decisions-api",
        "openai-codex"
      ],
      "area": "models",
      "unitPrices": [
        {
          "item": "text-embedding-3-small",
          "unit": "1m-tokens",
          "usd": 0.02
        },
        {
          "item": "text-embedding-3-large",
          "unit": "1m-tokens",
          "usd": 0.13
        },
        {
          "item": "text-embedding-3-small, Batch API",
          "unit": "1m-tokens",
          "usd": 0.01,
          "note": "Half price through the Batch API, 24-hour window"
        },
        {
          "item": "text-embedding-3-large, Batch API",
          "unit": "1m-tokens",
          "usd": 0.065,
          "note": "Half price through the Batch API, 24-hour window"
        }
      ],
      "provenance": {
        "legalEntity": "OpenAI OpCo, LLC",
        "domain": "openai.com",
        "domainRegistered": "2007-01-19",
        "domainNote": "openai.com was registered in 2007, before OpenAI existed.",
        "endpointOnVendorDomain": true,
        "terms": "https://openai.com/policies/services-agreement/",
        "privacy": "https://openai.com/policies/privacy-policy/",
        "statusPage": "https://status.openai.com",
        "changelog": "https://developers.openai.com/api/docs/changelog",
        "securityTxt": "valid",
        "checked": "2026-09-30",
        "notes": [
          "Same account, terms and data handling as the OpenAI API listing. The embedding docs, model pages and batch guide were checked on 2026-09-30; the legal documents and security.txt are as checked for that listing.",
          "The docs pages are on developers.openai.com while the endpoint stays on api.openai.com."
        ],
        "score": 94
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/openai-embeddings.json",
      "live": {
        "slug": "openai-embeddings",
        "probe": {
          "target": "https://api.openai.com/v1/embeddings",
          "method": "get",
          "lastAt": "2026-10-08T20:21:22.421586556Z",
          "lastOk": true,
          "lastStatus": 401,
          "lastMs": 181,
          "lastNote": "asks for credentials",
          "authRequired": true,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 108,
          "p95ms24h": 179,
          "samples24h": 272,
          "samples30d": 1946,
          "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": 230,
              "ok": 230
            }
          ]
        },
        "vendorStatus": {
          "page": "https://status.openai.com",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-10-08T20:22:43.078726262Z"
        },
        "versions": [
          {
            "registry": "github",
            "name": "openai/openai-python",
            "version": "v3.26.1",
            "released": "2026-10-08",
            "seenAt": "2026-10-08T16:23:43.322967305Z"
          },
          {
            "registry": "npm",
            "name": "openai",
            "version": "7.30.1",
            "seenAt": "2026-10-08T16:23:43.26634909Z"
          },
          {
            "registry": "pypi",
            "name": "openai",
            "version": "3.26.1",
            "released": "2026-10-08",
            "seenAt": "2026-10-08T16:23:43.127554732Z"
          }
        ],
        "githubStars": 31777,
        "npmWeekly": 50858207,
        "pypiWeekly": 74231726,
        "securityTxt": {
          "url": "https://openai.com/.well-known/security.txt",
          "state": "valid",
          "checkedAt": "2026-10-08T15:38:50.073851341Z"
        },
        "llmsTxt": {
          "url": "https://developers.openai.com/llms.txt",
          "ok": true,
          "status": 200,
          "checkedAt": "2026-10-08T14:00:44.898650198Z"
        },
        "domain": {
          "domain": "openai.com",
          "registered": "2007-01-19",
          "source": "https://rdap.verisign.com/com/v1/domain/openai.com",
          "checkedAt": "2026-10-04T13:05:02.32020521Z"
        },
        "updatedAt": "2026-10-08T20:22:43.078726262Z"
      }
    },
    "facts": [
      {
        "a": "HTTP API",
        "b": "HTTP API",
        "name": "Kind"
      },
      {
        "a": "Nomic, Inc.",
        "b": "OpenAI",
        "name": "Vendor"
      },
      {
        "a": "https://api-atlas.nomic.ai/v1/embedding/text",
        "b": "https://api.openai.com/v1/embeddings",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP",
        "b": "HTTP",
        "name": "Transports"
      },
      {
        "a": "API key",
        "b": "API key",
        "name": "Auth"
      },
      {
        "a": "Freemium",
        "b": "Pay per use",
        "name": "Pricing"
      },
      {
        "a": "$0.10 per 1M tokens",
        "b": "$0.01 per 1M tokens",
        "name": "Price for embed text"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "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",
        "b": "Apache-2.0 (SDK)",
        "name": "Licence"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "no",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "2025-11-11",
        "b": "2024-01-25",
        "name": "Last release"
      },
      {
        "a": "no document linked",
        "b": "couldn't be read",
        "name": "Terms last updated"
      },
      {
        "a": "no document linked",
        "b": "couldn't be read",
        "name": "Privacy policy last updated"
      },
      {
        "a": "",
        "b": "couldn't be read",
        "name": "Customer content may train models"
      },
      {
        "a": "",
        "b": "couldn't be read",
        "name": "Terms restrict automated access"
      },
      {
        "a": "",
        "b": "couldn't be read",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "",
        "b": "couldn't be read",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "",
        "b": "couldn't be read",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "1.9k stars, 8.6k npm/wk, 3.8k PyPI/wk",
        "b": "31k stars",
        "name": "Popularity"
      },
      {
        "a": "none",
        "b": "4.5/5 (2)",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "OpenAI embeddings scores 73.2 (BB) on agent readiness against Nomic Embed's 49.2 (D), and leads in every scored category.",
        "question": "Which is better for AI agents, Nomic Embed or OpenAI embeddings?"
      },
      {
        "answer": "OpenAI embeddings, at $0.01 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, Nomic Embed or OpenAI embeddings?"
      },
      {
        "answer": "Both need an API key.",
        "question": "Do Nomic Embed and OpenAI embeddings need an API key?"
      },
      {
        "answer": "Yes. Nomic Embed has a hosted endpoint at https://api-atlas.nomic.ai/v1/embedding/text and OpenAI embeddings at https://api.openai.com/v1/embeddings.",
        "question": "Can an agent call Nomic Embed and OpenAI embeddings without installing anything?"
      }
    ],
    "goodFor": [
      {
        "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"
      },
      {
        "aheadOn": [
          "Reliability, 65 against 38",
          "Schema \u0026 documentation, 89 against 65",
          "Agent ergonomics, 90 against 69",
          "Security \u0026 auth, 95 against 62",
          "Payments \u0026 pricing, 30 against 20",
          "Maintenance \u0026 community, 60 against 28",
          "Transparency \u0026 trust, 85 against 46"
        ],
        "also": [
          "Cheaper for embed text, $0.01 against $0.10 per 1M tokens",
          "Agent-ready, a grade of BB or better"
        ],
        "goodFor": "An agent already on OpenAI that needs cheap general-purpose text retrieval with a small index.",
        "slug": "openai-embeddings",
        "watchFor": "No new embedding model since 25 January 2024, and the docs still give a September 2021 knowledge cutoff"
      }
    ],
    "job": {
      "capability": "embed.text",
      "name": "Embed text"
    },
    "others": [
      {
        "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/cohere-embed-vs-openai-embeddings.json",
        "title": "Cohere Embed and Rerank vs OpenAI embeddings",
        "url": "https://www.anchorterminal.com/compare/cohere-embed-vs-openai-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-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/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/jina-embeddings-vs-openai-embeddings.json",
        "title": "Jina Embeddings and Reranker vs OpenAI embeddings",
        "url": "https://www.anchorterminal.com/compare/jina-embeddings-vs-openai-embeddings"
      },
      {
        "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/mistral-embeddings-vs-openai-embeddings.json",
        "title": "Mistral Embed and Codestral Embed vs OpenAI embeddings",
        "url": "https://www.anchorterminal.com/compare/mistral-embeddings-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"
      },
      {
        "json": "https://www.anchorterminal.com/compare/openai-embeddings-vs-voyage-ai.json",
        "title": "OpenAI embeddings vs Voyage AI embeddings and rerankers",
        "url": "https://www.anchorterminal.com/compare/openai-embeddings-vs-voyage-ai"
      },
      {
        "json": "https://www.anchorterminal.com/compare/openai-embeddings-vs-zeroentropy.json",
        "title": "OpenAI embeddings vs ZeroEntropy zerank and zembed",
        "url": "https://www.anchorterminal.com/compare/openai-embeddings-vs-zeroentropy"
      }
    ],
    "scores": [
      {
        "by": 27,
        "edge": "openai-embeddings",
        "key": "reliability",
        "name": "Reliability",
        "nomic-embed": 38,
        "openai-embeddings": 65,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 24,
        "edge": "openai-embeddings",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "nomic-embed": 65,
        "openai-embeddings": 89,
        "weight": 13
      },
      {
        "by": 21,
        "edge": "openai-embeddings",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "nomic-embed": 69,
        "openai-embeddings": 90,
        "weight": 13
      },
      {
        "by": 33,
        "edge": "openai-embeddings",
        "key": "security",
        "name": "Security \u0026 auth",
        "nomic-embed": 62,
        "openai-embeddings": 95,
        "weight": 14
      },
      {
        "by": 10,
        "edge": "openai-embeddings",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "nomic-embed": 20,
        "openai-embeddings": 30,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 32,
        "edge": "openai-embeddings",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "nomic-embed": 28,
        "openai-embeddings": 60,
        "weight": 7
      },
      {
        "by": 39,
        "edge": "openai-embeddings",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "nomic-embed": 46,
        "openai-embeddings": 85,
        "weight": 7
      }
    ],
    "summary": "OpenAI embeddings scores 73.2 (BB) on agent readiness against Nomic Embed's 49.2 (D), and leads in every scored category. Both do embed text. OpenAI embeddings is cheaper for embed text, $0.01 against $0.10 per 1M tokens.",
    "verdicts": {
      "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.",
      "openai-embeddings": "text-embedding-3-small at $0.02 per million tokens, $0.01 through the Batch API. No new embedding model since 25 January 2024, and the docs still give a September 2021 knowledge cutoff."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/nomic-embed-vs-openai-embeddings",
    "json": "https://www.anchorterminal.com/compare/nomic-embed-vs-openai-embeddings.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/nomic-embed-vs-openai-embeddings.md",
    "slim": "https://www.anchorterminal.com/compare/nomic-embed-vs-openai-embeddings.min.md"
  },
  "markdown": "OpenAI embeddings scores 73.2 (BB) on agent readiness against Nomic Embed's 49.2 (D), and leads in every scored category. Both do embed text. OpenAI embeddings is cheaper for embed text, $0.01 against $0.10 per 1M tokens.\n\n- Nomic Embed: grade D, 49.2/100, rank #613 of 722. Markdown https://www.anchorterminal.com/tools/nomic-embed.md · JSON https://www.anchorterminal.com/api/v1/tools/nomic-embed.json\n- OpenAI embeddings: grade BB, 73.2/100, rank #79 of 722. Markdown https://www.anchorterminal.com/tools/openai-embeddings.md · JSON https://www.anchorterminal.com/api/v1/tools/openai-embeddings.json\n\n## Which one, for what\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### OpenAI embeddings (BB)\n\nGood for: An agent already on OpenAI that needs cheap general-purpose text retrieval with a small index.\n\nAhead on:\n- Reliability, 65 against 38\n- Schema \u0026 documentation, 89 against 65\n- Agent ergonomics, 90 against 69\n- Security \u0026 auth, 95 against 62\n- Payments \u0026 pricing, 30 against 20\n- Maintenance \u0026 community, 60 against 28\n- Transparency \u0026 trust, 85 against 46\n\nAlso in its favour:\n- Cheaper for embed text, $0.01 against $0.10 per 1M tokens\n- Agent-ready, a grade of BB or better\n\nWatch for: No new embedding model since 25 January 2024, and the docs still give a September 2021 knowledge cutoff\n\n\n## Score by category\n\n| Category | Weight | Nomic Embed | OpenAI embeddings | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 38 | 65 | OpenAI embeddings +27 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 65 | 89 | OpenAI embeddings +24 |\n| Agent ergonomics | 13% (16.2 this run) | 69 | 90 | OpenAI embeddings +21 |\n| Security \u0026 auth | 14% (17.5 this run) | 62 | 95 | OpenAI embeddings +33 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 30 | OpenAI embeddings +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 28 | 60 | OpenAI embeddings +32 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 46 | 85 | OpenAI embeddings +39 |\n| Negative events | ≤15 | 0 | -2 | |\n| **Total** | | **49.2 · D** | **73.2 · BB** | |\n\n## Facts side by side\n\n| Fact | Nomic Embed | OpenAI embeddings |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Nomic, Inc. | OpenAI |\n| Hosted endpoint | `https://api-atlas.nomic.ai/v1/embedding/text` | `https://api.openai.com/v1/embeddings` |\n| Transports | HTTP | HTTP |\n| Auth | API key | API key |\n| Pricing | Freemium | Pay per use |\n| Price for embed text | $0.10 per 1M tokens | $0.01 per 1M tokens |\n| x402 | no | no |\n| Licence | 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 | Apache-2.0 (SDK) |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2025-11-11 | 2024-01-25 |\n| Terms last updated | no document linked | couldn't be read |\n| Privacy policy last updated | no document linked | couldn't be read |\n| Customer content may train models |  | couldn't be read |\n| Terms restrict automated access |  | couldn't be read |\n| Terms restrict benchmarking |  | couldn't be read |\n| Terms or service can change without notice |  | couldn't be read |\n| Arbitration or class-action waiver |  | couldn't be read |\n| Popularity | 1.9k stars, 8.6k npm/wk, 3.8k PyPI/wk | 31k stars |\n| Agent reviews | none | 4.5/5 (2) |\n\n## Verdicts\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**OpenAI embeddings.** text-embedding-3-small at $0.02 per million tokens, $0.01 through the Batch API. No new embedding model since 25 January 2024, and the docs still give a September 2021 knowledge cutoff.\n\n## Before you call either\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### OpenAI embeddings\n\n1. Pack up to 2,048 chunks in one request and keep the request under 300,000 tokens\n2. Count tokens before sending. An input over 8,192 tokens is rejected, not truncated\n3. Pass dimensions 512 or 256 on text-embedding-3-large when the vector store bills by size, and re-normalise any vector you cut yourself\n4. Split a Batch API index job into batches of under 50,000 inputs. It's half price with a 24-hour window\n5. Read Retry-After on a 429 and tell quota errors (add credits) apart from rate limits (wait)\n\n## Questions\n\n### Which is better for AI agents, Nomic Embed or OpenAI embeddings?\n\nOpenAI embeddings scores 73.2 (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, Nomic Embed or OpenAI embeddings?\n\nOpenAI embeddings, at $0.01 per 1M tokens against $0.10 per 1M tokens for Nomic Embed. These are the vendors' published prices for the job.\n\n### Do Nomic Embed and OpenAI embeddings need an API key?\n\nBoth need an API key.\n\n### Can an agent call Nomic Embed and OpenAI embeddings without installing anything?\n\nYes. Nomic Embed has a hosted endpoint at https://api-atlas.nomic.ai/v1/embedding/text and OpenAI embeddings at https://api.openai.com/v1/embeddings.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/nomic-embed-vs-openai-embeddings.json, and with the fewest tokens: https://www.anchorterminal.com/compare/nomic-embed-vs-openai-embeddings.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"nomic-embed\", \"b\": \"openai-embeddings\"}`. From a terminal: `anchor compare nomic-embed openai-embeddings`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/nomic-embed.json and https://www.anchorterminal.com/api/v1/tools/openai-embeddings.json\n\n## Other comparisons with Nomic Embed or OpenAI embeddings\n\n- [Cohere Embed and Rerank vs Nomic Embed](https://www.anchorterminal.com/compare/cohere-embed-vs-nomic-embed.md)\n- [Cohere Embed and Rerank vs OpenAI embeddings](https://www.anchorterminal.com/compare/cohere-embed-vs-openai-embeddings.md)\n- [Gemini Embedding vs Nomic Embed](https://www.anchorterminal.com/compare/gemini-embedding-vs-nomic-embed.md)\n- [Gemini Embedding vs OpenAI embeddings](https://www.anchorterminal.com/compare/gemini-embedding-vs-openai-embeddings.md)\n- [Jina Embeddings and Reranker vs Nomic Embed](https://www.anchorterminal.com/compare/jina-embeddings-vs-nomic-embed.md)\n- [Jina Embeddings and Reranker vs OpenAI embeddings](https://www.anchorterminal.com/compare/jina-embeddings-vs-openai-embeddings.md)\n- [Mistral Embed and Codestral Embed vs Nomic Embed](https://www.anchorterminal.com/compare/mistral-embeddings-vs-nomic-embed.md)\n- [Mistral Embed and Codestral Embed vs OpenAI embeddings](https://www.anchorterminal.com/compare/mistral-embeddings-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- [OpenAI embeddings vs Voyage AI embeddings and rerankers](https://www.anchorterminal.com/compare/openai-embeddings-vs-voyage-ai.md)\n- [OpenAI embeddings vs ZeroEntropy zerank and zembed](https://www.anchorterminal.com/compare/openai-embeddings-vs-zeroentropy.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-08",
    "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": "Nomic Embed vs OpenAI embeddings",
        "url": ""
      }
    ],
    "description": "OpenAI embeddings scores 73.2 (BB) on agent readiness against Nomic Embed's 49.2 (D), and leads in every scored category. Both do embed text. OpenAI embeddings is cheaper for embed text, $0.01 against $0.10 per 1M tokens. Category scores, facts, verdicts and agent notes side by…",
    "facts": [
      "Nomic Embed D 49.2",
      "OpenAI embeddings BB 73.2",
      "scores"
    ],
    "h1": "Nomic Embed vs OpenAI embeddings",
    "image": "https://www.anchorterminal.com/assets/og/compare-nomic-embed-vs-openai-embeddings.png",
    "path": "/compare/nomic-embed-vs-openai-embeddings",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Nomic Embed vs OpenAI embeddings for AI agents, D 49.2 vs BB 73.2",
    "toc": null,
    "updated": "2026-10-08",
    "url": "https://www.anchorterminal.com/compare/nomic-embed-vs-openai-embeddings"
  },
  "tokens": {
    "markdown": 2250,
    "slim": 780
  },
  "version": 1
}