{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/embeddings.rerank-candidates/",
    "json": "https://www.anchorterminal.com/niches/embeddings.rerank-candidates/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/embeddings.rerank-candidates/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/embeddings.rerank-candidates/index.min.md"
  },
  "markdown": "Two or three companies' docs show a full fit.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 2 | 3 | 14 | 8 | 7 |\n\n## What counts as done\n\nOne call takes the query and all candidates and returns each candidate's index with a relevance score, sorted or sortable, with a documented per-document token limit and truncation behaviour and a published billing unit.\n\nMeasured, for our own tests: 50 candidates reranked within 1 second at p95, and nDCG@10 above the first-stage order on the labelled set.\n\nHow agents ask for it: rerank these results; which of these chunks answers the question; improve the precision of my RAG; sort these 50 passages by relevance\n\n## Does the job\n\nThe docs show it meets the test above, and nothing we read says otherwise.\n\n- **Jina Embeddings and Reranker (Jina AI GmbH)**: POST /v1/rerank returns candidates sorted by relevance_score with their index, top_n is optional, max_doc_length defaults to 8,192 on v3.5 in a 131,072-token window, and the catalogue bills $0.05 per million tokens. p95 and nDCG unmeasured.\n- **Voyage AI embeddings and rerankers (Voyage AI Innovations, Inc.)**: One rerank call takes a query and up to 1,000 documents, with top_k, per-model query and query-plus-document token limits, truncation true or false documented, and per-token prices. p95 and nDCG unmeasured.\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Cohere Embed and Rerank (Cohere Inc.)**: One call returns index and relevance_score with top_n; max_tokens_per_doc defaults to 4,096 and truncates silently, and the billing unit is unclear, with billed_units carrying both tokens and search_units. Accounts report large quality gains.\n- **NVIDIA NeMo Retriever Embedding and Reranking NIMs (NVIDIA Corporation)**: /v1/ranking scores up to 512 passages in one call and returns index and logit sorted descending, with truncate NONE or END documented, but there is no top-n field and billing is per GPU, not per call.\n- **ZeroEntropy zerank and zembed (ZeroEntropy, Inc.)**: The hosted rerank endpoint is gone. zerank-2 is Apache 2.0 with a Sentence Transformers route and 32,768-token context, but a May 2026 breaking change made predict() return raw logits, and no per-call limits or billing remain.\n\n- not this job: Amazon Nova Multimodal Embeddings (Amazon Web Services, Inc.): An embedding model only; no rerank call in the Nova guide or schema.\n- not this job: EmbeddingGemma 2 (Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author)): An embedding model; no reranking head or scoring mode.\n- not this job: EmbeddingGemma 300M (Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author)): An embedding model; no reranking mode.\n- not this job: Gemini Embedding (Google LLC): No rerank endpoint in the embeddings guide or model page.\n- not this job: Granite Embedding Small English R2 (International Business Machines Corporation): A bi-encoder only; no reranking mode in this listing.\n- not this job: jina-embeddings-v5-omni-small (Jina AI GmbH, a subsidiary of Elastic N.V. (per the jina-embeddings listing's 2 October 2026 check)): An embedding model; no reranking head.\n- not this job: Mistral Embed and Codestral Embed (Mistral AI (RCS Paris 952 418 325)): No rerank endpoint in the OpenAPI document.\n- not this job: Nomic Embed (Nomic, Inc.): No rerank endpoint in the API reference.\n- not this job: OpenAI embeddings (OpenAI OpCo, LLC): No rerank endpoint.\n- not this job: Qwen3-Embedding-0.6B (Alibaba Cloud (the registrant of qwen.ai per RDAP, carried from the Qwen3.8-27B check)): An embedding model; the Qwen3-Reranker models are separate repositories, not this listing.\n- not this job: Qwen3-Embedding-4B (Alibaba Cloud (named in the copyright line of the 8B sibling's Apache 2.0 licence; this repository has no LICENSE file)): An embedding model; the Qwen3-Reranker models are separate repositories, not this listing.\n- not this job: Qwen3-Embedding-8B (Alibaba Cloud (named in the licence's copyright line)): An embedding model; the Qwen3-Reranker models are separate repositories, not this listing.\n- not this job: Qwen3-VL-Embedding-2B (Alibaba Cloud (RDAP names Alibaba Cloud (Singapore) Private Limited as the registrant of qwen.ai)): An embedding model; the Qwen3-VL-Reranker models are separate repositories, not this listing.\n- not this job: Qwen3-VL-Embedding-8B (Alibaba Group (Tongyi Lab, named in the copyright line of the GitHub repository's Apache 2.0 licence)): An embedding model; the Qwen3-VL-Reranker models are separate repositories, not this listing.\n\n## What stops agents finishing\n\n- default per-document token cap truncates long chunks (Cohere max_tokens_per_doc 4,096)\n- no top-n field, so the agent must sort and cut (NeMo Retriever /v1/ranking)\n- billing unit unclear (searches against tokens)\n- the reranker only reorders what the candidate stage found\n\n## Around it\n\nBefore: vector-search.hybrid-keyword, embeddings.index-docs-for-rag. After: company-knowledge.cited-answer.\n\n## Where this comes from\n\nWeight 8 of 100 in Embeddings \u0026 rerankers: 7 of 62 accounts (91 account-use-case tags, accounts counted in each use case they fit, scaled to 100 and rounded by hand); every account that tried a reranker called it a large gain; fewer accounts than its importance in threads suggests, so held at the count\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/embeddings.rerank-candidates.json, or the MCP tool get_use_case with id embeddings.rerank-candidates. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Rerank first-stage results before they reach the model",
        "url": ""
      }
    ],
    "description": "Rerank first-stage results before they reach the model: 2 companies fully do it, 3 with a limit, 14 carry the tag. Every listing in Embeddings \u0026 rerankers with the reason and a source.",
    "facts": null,
    "h1": "Rerank first-stage results before they reach the model",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/embeddings.rerank-candidates/",
    "published": "",
    "section": "agents",
    "title": "Rerank first-stage results before they reach the model | Anchor…",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/embeddings.rerank-candidates/"
  },
  "tokens": {
    "markdown": 1600,
    "slim": 280
  },
  "version": 1
}
