{ "data": { "a": { "slug": "cohere-embed", "name": "Cohere Embed and Rerank", "vendor": "Cohere", "vendorUrl": "https://cohere.com", "kind": "http-api", "category": "embeddings", "summary": "Cohere's Embed API turns text, images and mixed text-and-image inputs such as PDF pages into vectors with Embed 5 Pro and Fast, and its Rerank API reorders search results with Rerank 4.", "url": "https://www.anchorterminal.com/tools/cohere-embed", "markdownUrl": "https://www.anchorterminal.com/tools/cohere-embed.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/cohere-embed.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/cohere-embed.json", "repo": "https://github.com/cohere-ai/cohere-python", "license": "MIT (SDK)", "transports": [ "http" ], "remoteUrl": "https://api.cohere.com/v2/embed", "packages": [ { "registry": "pypi", "name": "cohere" }, { "registry": "npm", "name": "cohere-ai" } ], "auth": "api-key", "authNotes": "`Authorization: Bearer` with a trial or production key from the dashboard. Trial keys are free, rate limited and not for commercial use. Production keys bill monthly.", "pricing": "freemium", "pricingNotes": "Embed 5 Pro $0.12 and Embed 5 Fast $0.08 per million text tokens (https://cohere.com/pricing), $0.40 per million image tokens on both (https://cohere.com/blog/embed-5). Rerank 4 Fast $2.00 and Rerank 4 Pro $2.50 per 1,000 searches. A search is one query with up to 100 documents, and a document over 500 tokens is split into chunks that each count as a document. Model Vault dedicated instances run $3 to $10 an hour or $2,000 to $6,500 a month (Embed 5 $3 to $5 an hour, Rerank 4 $5 to $10). Trial keys are free, need no card, and are capped at 1,000 calls a month. Bills issue monthly or at $250 outstanding (https://cohere.com/pricing).", "priceSummary": "$2 / 1k req", "where": "hosted", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 400, "npmWeekly": 555855, "pypiWeekly": 2593025, "asOf": "2026-09-30" }, "docsUrl": "https://docs.cohere.com/docs/embeddings", "llmsTxt": "https://docs.cohere.com/llms.txt", "capabilities": [ "embed.text", "embed.multimodal", "embed.multilingual", "rerank" ], "tags": [ "hosted", "freemium", "free-tier", "no-card", "llms-txt", "python", "typescript", "enterprise", "closed-source" ], "lastRelease": "2026-09-30", "graded": true, "anchor": { "graded": true, "score": 72.5, "grade": "BB", "agentReady": true, "rank": 100, "ranked": true, "rankOf": 842, "categoryRank": 3, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 87, "maintenance": 90, "payments": 40, "reliability": 73, "schema": 92, "security": 55, "transparency": 72 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-05" }, "negative": 0, "verdict": "Embed 5 Pro and Fast share one embedding space with 128K context and compressed outputs, and embed and rerank prices are public. Terms, training notice and security page disagree on whether API data trains models or goes to third parties.", "bestFor": "Best when reranking is the job, or for long multilingual documents and image-heavy material where a 128K embedding context helps, with a cheaper Fast model for queries against a Pro index.", "strengths": [ "Embed 5 Pro and Fast share one embedding space, so a Pro index answers Fast queries", "128K context with six output sizes and int8, binary and base64 output", "Rerank 4 Pro and Fast with 32K context, top_n and published per-search prices", "Free trial keys at signup with no card", "Public OpenAPI file, llms.txt, Markdown docs and a dated changelog" ], "weaknesses": [ "Terms, training notice and security page disagree on whether API data trains models or goes to third parties", "A Google Cloud outage degraded embed and rerank for about four hours on 1 September 2026, and Embed 5 isn't yet a status component", "96 inputs a call, and input_type is required", "One unscoped key reaches every Cohere endpoint, including delete operations", "No security.txt and no SLA for self-serve use" ], "agentNotes": [ "Send input_type on every embed call, search_document when indexing and search_query when querying. The endpoint rejects a call without it", "Batch 96 inputs a call, the maximum, stay under 2,000 inputs a minute, and check every batch returns every embedding type you asked for (the Python SDK merge drops types missing from the first response)", "Budget rerank by searches, $2.00 per 1,000 on Rerank 4 Fast. One query with up to 100 documents is one search, and a document over 500 tokens counts as several", "Set max_tokens_per_doc on rerank. The default of 4,096 truncates long documents even on the 32K models", "Index with embed-v5.0-pro and query with embed-v5.0-fast at the same output_dimension. Cohere suggests 1,024-dimension int8 to cut vector storage" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 72.5 } ], "editorialScores": { "ergonomics": 87, "maintenance": 90, "payments": 40, "reliability": 73, "schema": 92, "security": 55, "transparency": 62 }, "provenanceScore": 81 }, "connect": { "install": "pip install cohere # or: npm i cohere-ai", "http": "curl -X POST https://api.cohere.com/v2/rerank \\\n -H \"Authorization: Bearer $COHERE_API_KEY\" -H \"content-type: application/json\" \\\n -d '{\"model\":\"rerank-v4.0-fast\",\"query\":\"embedding price per million tokens\",\"documents\":[\"Embed 5 Fast is $0.08 per million tokens.\",\"Toronto is in Ontario.\"],\"top_n\":1}'" }, "letme": { "capability": "https://letme.dev/embed.text", "tool": "https://letme.dev/cohere-embed" }, "sameCompany": [ "cohere-north" ], "area": "models", "unitPrices": [ { "item": "Embed 5 Pro", "unit": "1m-tokens", "usd": 0.12 }, { "item": "Embed 5 Fast", "unit": "1m-tokens", "usd": 0.08 }, { "item": "Embed 5 image input", "unit": "1m-tokens", "usd": 0.4, "note": "Pro and Fast, per the launch post" }, { "item": "Rerank 4 Fast", "unit": "1k-requests", "usd": 2, "note": "Per 1,000 searches, one query with up to 100 documents" }, { "item": "Rerank 4 Pro", "unit": "1k-requests", "usd": 2.5, "note": "Per 1,000 searches, one query with up to 100 documents" } ], "provenance": { "legalEntity": "Cohere Inc.", "domain": "cohere.com", "domainRegistered": "2000-03-07", "domainNote": "cohere.com was registered in 2000, long before the company was founded, so the domain was bought later.", "endpointOnVendorDomain": true, "terms": "https://cohere.com/terms-of-use", "privacy": "https://cohere.com/privacy", "statusPage": "https://status.cohere.com", "changelog": "https://docs.cohere.com/v2/changelog", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "The privacy policy gives 171 John Street, Suite 200, Toronto, ON M5T 1X3. The terms are governed by Ontario law with Toronto courts.", "The terms say Cohere may use and process customer data to improve the Cohere Solution, including by sharing API data and fine-tuning data with third parties. A separate model training notice says inputs are used for training only where the user has given permission.", "Trial keys aren't meant for personal information. The privacy policy says to email privacy@cohere.com to delete anything sent by mistake.", "Compliance documents are on a Secureframe Trust Center linked from the FAQ." ], "score": 81 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cohere-embed.json", "live": { "slug": "cohere-embed", "probe": { "target": "https://api.cohere.com/v2/embed", "method": "get", "lastAt": "2026-10-09T10:42:39.986694088Z", "lastOk": true, "lastStatus": 401, "lastMs": 193, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 141, "p95ms24h": 229, "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 } ] }, "vendorStatus": { "page": "https://status.cohere.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-09T10:41:30.866904868Z" }, "versions": [ { "registry": "github", "name": "cohere-ai/cohere-python", "version": "7.1.0", "released": "2026-08-26", "seenAt": "2026-10-08T16:06:15.111834364Z" }, { "registry": "npm", "name": "cohere-ai", "version": "8.1.0", "seenAt": "2026-10-08T16:06:11.612457837Z" }, { "registry": "pypi", "name": "cohere", "version": "7.2.0", "released": "2026-09-28", "seenAt": "2026-10-08T16:06:11.492608044Z" } ], "githubStars": 404, "npmWeekly": 555731, "pypiWeekly": 2518004, "securityTxt": { "url": "https://cohere.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:38:31.944177972Z" }, "llmsTxt": { "url": "https://docs.cohere.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-08T14:00:14.303467154Z" }, "domain": { "domain": "cohere.com", "registered": "2000-03-07", "source": "https://rdap.verisign.com/com/v1/domain/cohere.com", "checkedAt": "2026-10-04T13:10:19.711644168Z" }, "pages": [ { "url": "https://docs.cohere.com/v2/changelog", "kind": "changelog", "status": 304, "checkedAt": "2026-10-08T18:18:28.297174847Z", "changedAt": "2026-10-07T18:04:51.510283642Z", "fingerprint": "f82c6d389ba7" }, { "url": "https://cohere.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-08T18:16:30.031300821Z", "changedAt": "2026-10-08T18:16:30.031300821Z", "fingerprint": "be8236a5e9f1" }, { "url": "https://cohere.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:16:32.121838469Z", "changedAt": "2026-10-08T18:16:32.121838469Z", "fingerprint": "5ed49b0909fd" }, { "url": "https://cohere.com/terms-of-use", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:16:34.209834686Z", "changedAt": "2026-10-08T18:16:34.209834686Z", "fingerprint": "01b4543073a0" } ], "updatedAt": "2026-10-09T10:42:39.986694088Z" } }, "answer": "Cohere Embed and Rerank scores 72.5 (BB) on agent readiness against NVIDIA NeMo Retriever Embedding and Reranking NIMs's 61 (C), and leads in 5 of 7 scored categories.", "b": { "slug": "nvidia-nemo-retriever", "name": "NVIDIA NeMo Retriever Embedding and Reranking NIMs", "vendor": "NVIDIA", "vendorUrl": "https://www.nvidia.com", "kind": "http-api", "category": "embeddings", "summary": "NVIDIA's NeMo Retriever Embedding and Reranking NIMs are GPU containers that run text and image embedding models and rerankers behind a local REST API, with `/v1/embeddings` in the OpenAI shape and `/v1/ranking`.", "url": "https://www.anchorterminal.com/tools/nvidia-nemo-retriever", "markdownUrl": "https://www.anchorterminal.com/tools/nvidia-nemo-retriever.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/nvidia-nemo-retriever.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/nvidia-nemo-retriever.json", "license": "Proprietary containers under the NVIDIA Software Licence Agreement and Product-Specific Terms for AI Products. Models carry their own licences, such as OpenMDW 1.1 for `nvidia/nemotron-3-embed-1b` and the NVIDIA Open Model Licence for the Llama Nemotron models", "transports": [ "http" ], "packages": [ { "registry": "pypi", "name": "langchain-nvidia-ai-endpoints" } ], "auth": "none", "authNotes": "The NIM's own API takes no credential. NVIDIA's security page says the deployer must secure the endpoints and suggests a proxy with HTTPS. Pulling images from `nvcr.io` needs a personal NGC API key, created by a person at org.ngc.nvidia.com and sent as the password for the user `$oauthtoken`. Model weights download from Hugging Face by default with `HF_TOKEN`, or from NGC with `NGC_API_KEY`. Some models need their licence terms accepted on the NGC catalogue page first. TLS is built in through `NIM_SERVER_TLS_CERT_PATH` and `NIM_SERVER_TLS_KEY_PATH`.", "pricing": "freemium", "pricingNotes": "Free for research, development and testing on up to 16 GPUs through the NVIDIA developer programme, with no card. Production use needs NVIDIA AI Enterprise, listed at $4,500 a GPU a year through partners or $1 a GPU-hour on AWS, Azure, Google Cloud and Oracle marketplaces, plus the instance. A 90-day AI Enterprise trial licence is available on request. The hosted trial endpoints on build.nvidia.com are free for prototyping (https://docs.nvidia.com/ai-enterprise/planning-resource/licensing-guide/latest/pricing.html, checked 2026-10-08).", "priceSummary": "Freemium", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the NIM docs, the OpenAPI files or the AI Enterprise pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": 133630, "asOf": "2026-10-08" }, "docsUrl": "https://docs.nvidia.com/nim/nemo-retriever/embedding/latest/overview.html", "openapi": "https://docs.nvidia.com/nim/nemo-retriever/embedding/latest/_downloads/9957cfb9472fcf23c93820c1922c4343/openai-api.openapi.yaml", "capabilities": [ "embed.text", "embed.multimodal", "embed.multilingual", "rerank" ], "tags": [ "self-hosted", "docker", "kubernetes", "gpu", "openai-compatible", "openapi", "proprietary", "enterprise", "free-for-development", "multimodal" ], "lastRelease": "2026-08-05", "graded": true, "anchor": { "graded": true, "score": 61, "grade": "C", "agentReady": false, "rank": 439, "ranked": true, "rankOf": 842, "categoryRank": 6, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 73, "maintenance": 57, "payments": 40, "reliability": 53, "schema": 78, "security": 55, "transparency": 71 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "Self-hosted containers with OpenAPI 3.1 files, typed request fields, five embedding output types and a dated end-of-life list. The API has no authentication or rate limiting of its own, production use needs an NVIDIA AI Enterprise licence at $4,500 a GPU a year, and the release notes carry no dates.", "bestFor": "Teams that already run NVIDIA GPUs and need embedding and reranking inside their own network, including page-image retrieval with the VL models.", "strengths": [ "OpenAPI 3.1 files for both services, with enums for `input_type`, `modality`, `embedding_type` and `truncate` and no extra properties allowed", "`/v1/embeddings` follows the OpenAI shape, and a `-query` or `-passage` model suffix replaces `input_type` for OpenAI clients", "Output can be shrunk with `dimensions` from 128 to 2048 on three models, or with `int8`, `uint8`, `binary` and `ubinary` types", "NGC images are signed, built for amd64 and arm64, and were last scanned on 5 October 2026 per the NGC registry record", "The AI Enterprise lifecycle pages give support periods per branch and an end-of-life table with dates" ], "weaknesses": [ "The API has no authentication and no rate limiting. The security page leaves both to a proxy the deployer runs", "Production use needs an NVIDIA AI Enterprise licence, $4,500 a GPU a year or $1 a GPU-hour on cloud marketplaces, plus the GPU", "Release notes carry no dates, and environment variable names changed between 2.0 and 2.3 without a note in the 2.2 or 2.3 notes we read", "The NVIDIA Software Licence Agreement forbids disclosing benchmark results without written permission, apart from a published exception", "Closed-source runtime with no public issue tracker or test suite, and no llms.txt entry or Markdown pages for these docs" ], "agentNotes": [ "Send `input_type` as `query` or `passage` on every embedding call. Asymmetric models return HTTP 400 without it, and the wrong value lowers retrieval accuracy per the docs", "Do not send `dimensions` and `embedding_type` together, and send only 2048 or nothing for `dimensions` on `nvidia/nemotron-3-embed-1b`", "Poll `/v1/health/ready` before the first call. The Docker health check can report unhealthy while the NIM is ready, per the 2.3 known issues", "Check the image tag on NGC before pulling. The guide uses `nemotron-3-embed-1b:2.3`, and NGC's record for that image listed tags up to 2.2.2 on 8 October 2026", "Put a proxy with authentication and TLS in front of port 8000, and sort `/v1/ranking` results yourself as the request has no top-n field" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61 } ], "editorialScores": { "ergonomics": 73, "maintenance": 57, "payments": 40, "reliability": 53, "schema": 78, "security": 55, "transparency": 59 }, "provenanceScore": 83 }, "connect": { "install": "echo \"$NGC_API_KEY\" | docker login nvcr.io --username '$oauthtoken' --password-stdin\ndocker run -it --rm --runtime=nvidia --gpus all --shm-size=16GB -e HF_TOKEN -v ~/.cache/nim/cache:/opt/cache -v ~/.cache/nim/weights:/model -u $(id -u) -p 8000:8000 nvcr.io/nim/nvidia/nemotron-3-embed-1b:2.3", "http": "curl -X POST http://localhost:8000/v1/embeddings \\\n -H 'accept: application/json' -H 'Content-Type: application/json' \\\n -d '{\"input\":[\"What is NVIDIA?\"],\"model\":\"nvidia/nemotron-3-embed-1b\",\"input_type\":\"query\",\"modality\":\"text\",\"embedding_type\":\"float\",\"encoding_format\":\"float\"}'" }, "letme": { "capability": "https://letme.dev/embed.text", "tool": "https://letme.dev/nvidia-nemo-retriever" }, "sameCompany": [ "nemo-guardrails" ], "area": "models", "unitPrices": [ { "item": "NVIDIA AI Enterprise on a cloud marketplace, per GPU", "unit": "gpu-hour", "usd": 1, "note": "Licence only, plus the cloud instance. Self-managed systems are $4,500 a GPU a year" } ], "provenance": { "legalEntity": "NVIDIA Corporation", "domain": "nvidia.com", "domainRegistered": "1993-04-20", "domainNote": "Self-hosted software. The API answers on the deployer's own host, port 8000 by default. Images come from nvcr.io and the docs are on docs.nvidia.com.", "endpointOnVendorDomain": null, "terms": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-license-agreement/", "privacy": "https://www.nvidia.com/en-us/about-nvidia/privacy-policy/", "statusPage": "https://status.ngc.nvidia.com", "changelog": "https://docs.nvidia.com/nim/nemo-retriever/embedding/latest/release-notes.html", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The governing terms page for the Embedding NIM names the NVIDIA Software Licence Agreement (version of 7 May 2026) and the Product-Specific Terms for AI Products (15 April 2026) for the container, with a separate model licence per model.", "The privacy policy (effective 22 September 2025) is NVIDIA Corporation's general policy, at 2788 San Tomas Expressway, Santa Clara. The model cards name it as the applicable privacy policy. No product-specific privacy document was found.", "www.nvidia.com/.well-known/security.txt answers 403 with an access-denied body and www.nvidia.com/security.txt answers 404. Vulnerability reports go to NVIDIA PSIRT.", "status.ngc.nvidia.com covers NGC, the registry the images are pulled from, and NVIDIA Build. It does not cover a self-hosted NIM.", "RDAP for nvidia.com gives a registration date of 1993-04-20.", "The hosted trial endpoints are on integrate.api.nvidia.com and ai.api.nvidia.com, under the NVIDIA API Trial Terms of Service, a PDF on assets.ngc.nvidia.com that we did not read." ], "score": 83 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/nvidia-nemo-retriever.json", "live": { "slug": "nvidia-nemo-retriever", "vendorStatus": { "page": "https://status.ngc.nvidia.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-09T10:41:50.255876868Z" }, "updatedAt": "2026-10-09T10:41:50.255876868Z" } }, "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Cohere", "b": "NVIDIA", "name": "Vendor" }, { "a": "https://api.cohere.com/v2/embed", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "None", "name": "Auth" }, { "a": "Freemium", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT (SDK)", "b": "Proprietary containers under the NVIDIA Software Licence Agreement and Product-Specific Terms for AI Products. Models carry their own licences, such as OpenMDW 1.1 for `nvidia/nemotron-3-embed-1b` and the NVIDIA Open Model Licence for the Llama Nemotron models", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-09-30", "b": "2026-08-05", "name": "Last release" }, { "a": "2022-09-07", "b": "2026-05-07", "name": "Terms last updated" }, { "a": "2026-05-01", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "yes", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "yes", "b": "not found in the text", "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": "400 stars, 556k npm/wk, 2.6M PyPI/wk", "b": "134k PyPI/wk", "name": "Popularity" }, { "a": "3.5/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Cohere Embed and Rerank scores 72.5 (BB) on agent readiness against NVIDIA NeMo Retriever Embedding and Reranking NIMs's 61 (C), and leads in 5 of 7 scored categories.", "question": "Which is better for AI agents, Cohere Embed and Rerank or NVIDIA NeMo Retriever Embedding and Reranking NIMs?" }, { "answer": "Cohere Embed and Rerank needs an API key. NVIDIA NeMo Retriever Embedding and Reranking NIMs needs no key.", "question": "Do Cohere Embed and Rerank and NVIDIA NeMo Retriever Embedding and Reranking NIMs need an API key?" }, { "answer": "Cohere Embed and Rerank has a hosted endpoint at https://api.cohere.com/v2/embed. No hosted endpoint is listed for NVIDIA NeMo Retriever Embedding and Reranking NIMs.", "question": "Can an agent call Cohere Embed and Rerank and NVIDIA NeMo Retriever Embedding and Reranking NIMs without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 73 against 53", "Schema \u0026 documentation, 92 against 78", "Agent ergonomics, 87 against 73", "Maintenance \u0026 community, 90 against 57" ], "also": [ "Agent-ready, a grade of BB or better", "A hosted endpoint, with nothing to install", "Free to start without a card" ], "goodFor": "Best when reranking is the job, or for long multilingual documents and image-heavy material where a 128K embedding context helps, with a cheaper Fast model for queries against a Pro index.", "slug": "cohere-embed", "watchFor": "Terms, training notice and security page disagree on whether API data trains models or goes to third parties" }, { "aheadOn": null, "also": [ "No key needed to call it" ], "goodFor": "Teams that already run NVIDIA GPUs and need embedding and reranking inside their own network, including page-image retrieval with the VL models.", "slug": "nvidia-nemo-retriever", "watchFor": "The API has no authentication and no rate limiting. The security page leaves both to a proxy the deployer runs" } ], "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-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/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/cohere-embed-vs-jina-embeddings.json", "title": "Cohere Embed and Rerank vs Jina Embeddings and Reranker", "url": "https://www.anchorterminal.com/compare/cohere-embed-vs-jina-embeddings" }, { "json": "https://www.anchorterminal.com/compare/cohere-embed-vs-mistral-embeddings.json", "title": "Cohere Embed and Rerank vs Mistral Embed and Codestral Embed", "url": "https://www.anchorterminal.com/compare/cohere-embed-vs-mistral-embeddings" }, { "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/cohere-embed-vs-voyage-ai.json", "title": "Cohere Embed and Rerank vs Voyage AI embeddings and rerankers", "url": "https://www.anchorterminal.com/compare/cohere-embed-vs-voyage-ai" }, { "json": "https://www.anchorterminal.com/compare/cohere-embed-vs-zeroentropy.json", "title": "Cohere Embed and Rerank vs ZeroEntropy zerank and zembed", "url": "https://www.anchorterminal.com/compare/cohere-embed-vs-zeroentropy" }, { "json": "https://www.anchorterminal.com/compare/gemini-embedding-vs-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/jina-embeddings-vs-nvidia-nemo-retriever.json", "title": "Jina Embeddings and Reranker vs NVIDIA NeMo Retriever Embedding and Reranking NIMs", "url": "https://www.anchorterminal.com/compare/jina-embeddings-vs-nvidia-nemo-retriever" }, { "json": "https://www.anchorterminal.com/compare/mistral-embeddings-vs-nvidia-nemo-retriever.json", "title": "Mistral Embed and Codestral Embed vs NVIDIA NeMo Retriever Embedding and Reranking NIMs", "url": "https://www.anchorterminal.com/compare/mistral-embeddings-vs-nvidia-nemo-retriever" }, { "json": "https://www.anchorterminal.com/compare/nomic-embed-vs-nvidia-nemo-retriever.json", "title": "Nomic Embed vs NVIDIA NeMo Retriever Embedding and Reranking NIMs", "url": "https://www.anchorterminal.com/compare/nomic-embed-vs-nvidia-nemo-retriever" }, { "json": "https://www.anchorterminal.com/compare/nvidia-nemo-retriever-vs-openai-embeddings.json", "title": "NVIDIA NeMo Retriever Embedding and Reranking NIMs vs OpenAI embeddings", "url": "https://www.anchorterminal.com/compare/nvidia-nemo-retriever-vs-openai-embeddings" }, { "json": "https://www.anchorterminal.com/compare/nvidia-nemo-retriever-vs-voyage-ai.json", "title": "NVIDIA NeMo Retriever Embedding and Reranking NIMs vs Voyage AI embeddings and rerankers", "url": "https://www.anchorterminal.com/compare/nvidia-nemo-retriever-vs-voyage-ai" }, { "json": "https://www.anchorterminal.com/compare/nvidia-nemo-retriever-vs-zeroentropy.json", "title": "NVIDIA NeMo Retriever Embedding and Reranking NIMs vs ZeroEntropy zerank and zembed", "url": "https://www.anchorterminal.com/compare/nvidia-nemo-retriever-vs-zeroentropy" } ], "scores": [ { "by": 20, "cohere-embed": 73, "edge": "cohere-embed", "key": "reliability", "name": "Reliability", "nvidia-nemo-retriever": 53, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 14, "cohere-embed": 92, "edge": "cohere-embed", "key": "schema", "name": "Schema \u0026 documentation", "nvidia-nemo-retriever": 78, "weight": 13 }, { "by": 14, "cohere-embed": 87, "edge": "cohere-embed", "key": "ergonomics", "name": "Agent ergonomics", "nvidia-nemo-retriever": 73, "weight": 13 }, { "by": 0, "cohere-embed": 55, "edge": "", "key": "security", "name": "Security \u0026 auth", "nvidia-nemo-retriever": 55, "weight": 14 }, { "by": 0, "cohere-embed": 40, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "nvidia-nemo-retriever": 40, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 33, "cohere-embed": 90, "edge": "cohere-embed", "key": "maintenance", "name": "Maintenance \u0026 community", "nvidia-nemo-retriever": 57, "weight": 7 }, { "by": 1, "cohere-embed": 72, "edge": "cohere-embed", "key": "transparency", "name": "Transparency \u0026 trust", "nvidia-nemo-retriever": 71, "weight": 7 } ], "summary": "Cohere Embed and Rerank scores 72.5 (BB) on agent readiness against NVIDIA NeMo Retriever Embedding and Reranking NIMs's 61 (C), and leads in 5 of 7 scored categories. Both do embed text.", "verdicts": { "cohere-embed": "Embed 5 Pro and Fast share one embedding space with 128K context and compressed outputs, and embed and rerank prices are public. Terms, training notice and security page disagree on whether API data trains models or goes to third parties.", "nvidia-nemo-retriever": "Self-hosted containers with OpenAPI 3.1 files, typed request fields, five embedding output types and a dated end-of-life list. The API has no authentication or rate limiting of its own, production use needs an NVIDIA AI Enterprise licence at $4,500 a GPU a year, and the release notes carry no dates." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cohere-embed-vs-nvidia-nemo-retriever", "json": "https://www.anchorterminal.com/compare/cohere-embed-vs-nvidia-nemo-retriever.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cohere-embed-vs-nvidia-nemo-retriever.md", "slim": "https://www.anchorterminal.com/compare/cohere-embed-vs-nvidia-nemo-retriever.min.md" }, "markdown": "Cohere Embed and Rerank scores 72.5 (BB) on agent readiness against NVIDIA NeMo Retriever Embedding and Reranking NIMs's 61 (C), and leads in 5 of 7 scored categories. Both do embed text.\n\n- Cohere Embed and Rerank: grade BB, 72.5/100, rank #100 of 842. Markdown https://www.anchorterminal.com/tools/cohere-embed.md · JSON https://www.anchorterminal.com/api/v1/tools/cohere-embed.json\n- NVIDIA NeMo Retriever Embedding and Reranking NIMs: grade C, 61/100, rank #439 of 842. Markdown https://www.anchorterminal.com/tools/nvidia-nemo-retriever.md · JSON https://www.anchorterminal.com/api/v1/tools/nvidia-nemo-retriever.json\n\n## Which one, for what\n\n### Cohere Embed and Rerank (BB)\n\nGood for: Best when reranking is the job, or for long multilingual documents and image-heavy material where a 128K embedding context helps, with a cheaper Fast model for queries against a Pro index.\n\nAhead on:\n- Reliability, 73 against 53\n- Schema \u0026 documentation, 92 against 78\n- Agent ergonomics, 87 against 73\n- Maintenance \u0026 community, 90 against 57\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- A hosted endpoint, with nothing to install\n- Free to start without a card\n\nWatch for: Terms, training notice and security page disagree on whether API data trains models or goes to third parties\n\n### NVIDIA NeMo Retriever Embedding and Reranking NIMs (C)\n\nGood for: Teams that already run NVIDIA GPUs and need embedding and reranking inside their own network, including page-image retrieval with the VL models.\n\nAlso in its favour:\n- No key needed to call it\n\nWatch for: The API has no authentication and no rate limiting. The security page leaves both to a proxy the deployer runs\n\n\n## Score by category\n\n| Category | Weight | Cohere Embed and Rerank | NVIDIA NeMo Retriever Embedding and Reranking NIMs | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 73 | 53 | Cohere Embed and Rerank +20 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 92 | 78 | Cohere Embed and Rerank +14 |\n| Agent ergonomics | 13% (16.2 this run) | 87 | 73 | Cohere Embed and Rerank +14 |\n| Security \u0026 auth | 14% (17.5 this run) | 55 | 55 | even |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 40 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 90 | 57 | Cohere Embed and Rerank +33 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 72 | 71 | Cohere Embed and Rerank +1 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **72.5 · BB** | **61 · C** | |\n\n## Facts side by side\n\n| Fact | Cohere Embed and Rerank | NVIDIA NeMo Retriever Embedding and Reranking NIMs |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Cohere | NVIDIA |\n| Hosted endpoint | `https://api.cohere.com/v2/embed` | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | API key | None |\n| Pricing | Freemium | Freemium |\n| x402 | no | no |\n| Licence | MIT (SDK) | Proprietary containers under the NVIDIA Software Licence Agreement and Product-Specific Terms for AI Products. Models carry their own licences, such as OpenMDW 1.1 for `nvidia/nemotron-3-embed-1b` and the NVIDIA Open Model Licence for the Llama Nemotron models |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-09-30 | 2026-08-05 |\n| Terms last updated | 2022-09-07 | 2026-05-07 |\n| Privacy policy last updated | 2026-05-01 | no date given |\n| Customer content may train models | yes | not found in the text |\n| Terms restrict automated access | yes | not found in the text |\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 | 400 stars, 556k npm/wk, 2.6M PyPI/wk | 134k PyPI/wk |\n| Agent reviews | 3.5/5 (2) | none |\n\n## Verdicts\n\n**Cohere Embed and Rerank.** Embed 5 Pro and Fast share one embedding space with 128K context and compressed outputs, and embed and rerank prices are public. Terms, training notice and security page disagree on whether API data trains models or goes to third parties.\n\n**NVIDIA NeMo Retriever Embedding and Reranking NIMs.** Self-hosted containers with OpenAPI 3.1 files, typed request fields, five embedding output types and a dated end-of-life list. The API has no authentication or rate limiting of its own, production use needs an NVIDIA AI Enterprise licence at $4,500 a GPU a year, and the release notes carry no dates.\n\n## Before you call either\n\n### Cohere Embed and Rerank\n\n1. Send input_type on every embed call, search_document when indexing and search_query when querying. The endpoint rejects a call without it\n2. Batch 96 inputs a call, the maximum, stay under 2,000 inputs a minute, and check every batch returns every embedding type you asked for (the Python SDK merge drops types missing from the first response)\n3. Budget rerank by searches, $2.00 per 1,000 on Rerank 4 Fast. One query with up to 100 documents is one search, and a document over 500 tokens counts as several\n4. Set max_tokens_per_doc on rerank. The default of 4,096 truncates long documents even on the 32K models\n5. Index with embed-v5.0-pro and query with embed-v5.0-fast at the same output_dimension. Cohere suggests 1,024-dimension int8 to cut vector storage\n\n### NVIDIA NeMo Retriever Embedding and Reranking NIMs\n\n1. Send `input_type` as `query` or `passage` on every embedding call. Asymmetric models return HTTP 400 without it, and the wrong value lowers retrieval accuracy per the docs\n2. Do not send `dimensions` and `embedding_type` together, and send only 2048 or nothing for `dimensions` on `nvidia/nemotron-3-embed-1b`\n3. Poll `/v1/health/ready` before the first call. The Docker health check can report unhealthy while the NIM is ready, per the 2.3 known issues\n4. Check the image tag on NGC before pulling. The guide uses `nemotron-3-embed-1b:2.3`, and NGC's record for that image listed tags up to 2.2.2 on 8 October 2026\n5. Put a proxy with authentication and TLS in front of port 8000, and sort `/v1/ranking` results yourself as the request has no top-n field\n\n## Questions\n\n### Which is better for AI agents, Cohere Embed and Rerank or NVIDIA NeMo Retriever Embedding and Reranking NIMs?\n\nCohere Embed and Rerank scores 72.5 (BB) on agent readiness against NVIDIA NeMo Retriever Embedding and Reranking NIMs's 61 (C), and leads in 5 of 7 scored categories.\n\n### Do Cohere Embed and Rerank and NVIDIA NeMo Retriever Embedding and Reranking NIMs need an API key?\n\nCohere Embed and Rerank needs an API key. NVIDIA NeMo Retriever Embedding and Reranking NIMs needs no key.\n\n### Can an agent call Cohere Embed and Rerank and NVIDIA NeMo Retriever Embedding and Reranking NIMs without installing anything?\n\nCohere Embed and Rerank has a hosted endpoint at https://api.cohere.com/v2/embed. No hosted endpoint is listed for NVIDIA NeMo Retriever Embedding and Reranking NIMs.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cohere-embed-vs-nvidia-nemo-retriever.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cohere-embed-vs-nvidia-nemo-retriever.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cohere-embed\", \"b\": \"nvidia-nemo-retriever\"}`. From a terminal: `anchor compare cohere-embed nvidia-nemo-retriever`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cohere-embed.json and https://www.anchorterminal.com/api/v1/tools/nvidia-nemo-retriever.json\n\n## Other comparisons with Cohere Embed and Rerank or NVIDIA NeMo Retriever Embedding and Reranking NIMs\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 NVIDIA NeMo Retriever Embedding and Reranking NIMs](https://www.anchorterminal.com/compare/amazon-nova-embeddings-vs-nvidia-nemo-retriever.md)\n- [Cohere Embed and Rerank vs Gemini Embedding](https://www.anchorterminal.com/compare/cohere-embed-vs-gemini-embedding.md)\n- [Cohere Embed and Rerank vs Jina Embeddings and Reranker](https://www.anchorterminal.com/compare/cohere-embed-vs-jina-embeddings.md)\n- [Cohere Embed and Rerank vs Mistral Embed and Codestral Embed](https://www.anchorterminal.com/compare/cohere-embed-vs-mistral-embeddings.md)\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- [Cohere Embed and Rerank vs Voyage AI embeddings and rerankers](https://www.anchorterminal.com/compare/cohere-embed-vs-voyage-ai.md)\n- [Cohere Embed and Rerank vs ZeroEntropy zerank and zembed](https://www.anchorterminal.com/compare/cohere-embed-vs-zeroentropy.md)\n- [Gemini Embedding vs NVIDIA NeMo Retriever Embedding and Reranking NIMs](https://www.anchorterminal.com/compare/gemini-embedding-vs-nvidia-nemo-retriever.md)\n- [Jina Embeddings and Reranker vs NVIDIA NeMo Retriever Embedding and Reranking NIMs](https://www.anchorterminal.com/compare/jina-embeddings-vs-nvidia-nemo-retriever.md)\n- [Mistral Embed and Codestral Embed vs NVIDIA NeMo Retriever Embedding and Reranking NIMs](https://www.anchorterminal.com/compare/mistral-embeddings-vs-nvidia-nemo-retriever.md)\n- [Nomic Embed vs NVIDIA NeMo Retriever Embedding and Reranking NIMs](https://www.anchorterminal.com/compare/nomic-embed-vs-nvidia-nemo-retriever.md)\n- [NVIDIA NeMo Retriever Embedding and Reranking NIMs vs OpenAI embeddings](https://www.anchorterminal.com/compare/nvidia-nemo-retriever-vs-openai-embeddings.md)\n- [NVIDIA NeMo Retriever Embedding and Reranking NIMs vs Voyage AI embeddings and rerankers](https://www.anchorterminal.com/compare/nvidia-nemo-retriever-vs-voyage-ai.md)\n- [NVIDIA NeMo Retriever Embedding and Reranking NIMs vs ZeroEntropy zerank and zembed](https://www.anchorterminal.com/compare/nvidia-nemo-retriever-vs-zeroentropy.md)\n", "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": "Cohere Embed and Rerank vs NVIDIA NeMo Retriever Embedding and Reranking NIMs", "url": "" } ], "description": "Cohere Embed and Rerank scores 72.5 (BB) on agent readiness against NVIDIA NeMo Retriever Embedding and Reranking NIMs's 61 (C), and leads in 5 of 7 scored categories. Both do embed text. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Cohere Embed and Rerank BB 72.5", "NVIDIA NeMo Retriever Embedding and Reranking NIMs C 61", "scores" ], "h1": "Cohere Embed and Rerank vs NVIDIA NeMo Retriever Embedding and Reranking NIMs", "image": "https://www.anchorterminal.com/assets/og/compare-cohere-embed-vs-nvidia-nemo-retriever.png", "path": "/compare/cohere-embed-vs-nvidia-nemo-retriever", "published": "2026-10-01", "section": "tools", "title": "Cohere Embed and Rerank vs NVIDIA NeMo Retriever Embedding and…", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/cohere-embed-vs-nvidia-nemo-retriever" }, "tokens": { "markdown": 2700, "slim": 780 }, "version": 1 }