{
  "schema_version": "rangoon.article.v1",
  "id": "https://rangoon.ai/insights/archive-cohere-rerank-3-5-december-2024/",
  "url": "https://rangoon.ai/insights/archive-cohere-rerank-3-5-december-2024/",
  "markdown_url": "https://rangoon.ai/insights/archive-cohere-rerank-3-5-december-2024/index.md",
  "json_url": "https://rangoon.ai/insights/archive-cohere-rerank-3-5-december-2024/index.json",
  "title": "Cohere’s Rerank 3.5 release changed both retrieval ranking and the API contract",
  "summary": "Cohere released Rerank v3.5 and a v2 Rerank API on December 2, 2024, adding a 4,096-token context limit and explicit model selection.",
  "language": "en",
  "author": {
    "name": "Rangoon Editorial",
    "url": "https://rangoon.ai/insights/editorial/"
  },
  "publisher": {
    "name": "Rangoon",
    "maintainer": "Hypler",
    "url": "https://rangoon.ai/"
  },
  "format": "News analysis",
  "topic": {
    "slug": "models",
    "label": "Models",
    "url": "https://rangoon.ai/insights/topics/models/"
  },
  "tags": [
    {
      "slug": "cohere",
      "label": "Cohere",
      "url": "https://rangoon.ai/insights/tags/cohere/"
    },
    {
      "slug": "rerank-3-5",
      "label": "Rerank 3.5",
      "url": "https://rangoon.ai/insights/tags/rerank-3-5/"
    },
    {
      "slug": "retrieval",
      "label": "retrieval",
      "url": "https://rangoon.ai/insights/tags/retrieval/"
    },
    {
      "slug": "search-ranking",
      "label": "search ranking",
      "url": "https://rangoon.ai/insights/tags/search-ranking/"
    }
  ],
  "dates": {
    "published": "2026-10-23",
    "updated": "2026-10-23",
    "event": "2024-12-02"
  },
  "event_source_id": 1,
  "retrospective": true,
  "reading_minutes": 3,
  "takeaways": [
    "Rerank v3.5 scored a query against candidate documents after retrieval, with a stated 4,096-token context limit.",
    "The v2 API made the model explicit and replaced a chunk-count control with a token-per-document control.",
    "Reranking can improve ordering only within the candidate set a first-stage retriever supplied."
  ],
  "source_note": "Historical reporting: Cohere released Rerank v3.5 and a v2 Rerank API on December 2, 2024. Its release notes state a 4,096-token context length, required model selection, and replacement of max_chunks_per_doc with max_tokens_per_doc, defaulting to 4096. A maintained models overview is later context only. Cohere’s performance positioning is not treated as an independent relevance measurement.",
  "sources": [
    {
      "id": 1,
      "title": "Cohere release notes: Rerank v3.5",
      "url": "https://docs.cohere.com/changelog/rerank-v3.5",
      "published": "2024-12-02"
    },
    {
      "id": 2,
      "title": "Cohere documentation: An Overview of Cohere’s Models",
      "url": "https://docs.cohere.com/v1/docs/models",
      "published": null
    }
  ],
  "image": {
    "url": "https://rangoon.ai/assets/editorial/archive-cohere-rerank-3-5-december-2024-diagram-v1.webp",
    "thumbnail_url": "https://rangoon.ai/assets/editorial/archive-cohere-rerank-3-5-december-2024-diagram-v1-thumb.webp",
    "alt": "Original models explanatory diagram, Two-stage retrieval and reranking contract. Labels: Query, Candidate index, Candidate set, 4K token cap, Rerank v3.5, Ordered results, Relevance labels. Source boundary: dated primary release reporting; original editorial analysis.",
    "type": "original-diagram",
    "caption": "Two-stage retrieval and reranking contract. Original Rangoon explanatory diagram: Source boundary: dated primary release reporting; original editorial analysis. No vendor interface, photograph, measurement result, or endorsement implied.",
    "credit": "Rangoon / Hypler",
    "source_url": "https://rangoon.ai/brand/",
    "rights_url": "https://rangoon.ai/terms/#media-use",
    "rights_note": "Hypler artwork permissions do not grant rights to third-party marks or imply endorsement."
  },
  "sections": [
    {
      "id": "december-event",
      "url": "https://rangoon.ai/insights/archive-cohere-rerank-3-5-december-2024/#december-event",
      "heading": "The December event paired a model release with an interface change",
      "paragraphs": [
        "Cohere announced its new Rerank model and v2 Rerank API on December 2, 2024. The release notes gave the model a 4,096-token context length and said that the v2 endpoint requires a model parameter. They also replaced max_chunks_per_doc with max_tokens_per_doc, whose default was 4096.",
        "This was more than a new name in a model catalog. An explicit model field makes model selection part of a caller’s contract, while a token-based document limit describes the input boundary differently from a count of chunks created elsewhere in an application. That change makes truncation policy visible at the integration boundary."
      ],
      "bullets": [],
      "source_ids": [
        1
      ]
    },
    {
      "id": "ranking-place",
      "url": "https://rangoon.ai/insights/archive-cohere-rerank-3-5-december-2024/#ranking-place",
      "heading": "Reranking acts after candidate retrieval, not before it",
      "paragraphs": [
        "A typical retrieval path first gathers candidate passages using a lexical, vector, or hybrid index, then asks a reranker to order that smaller set against the query. The reranker can make a more detailed comparison than a broad index lookup, but it cannot return a relevant document that the first stage never supplied. Candidate recall and reranking precision are therefore linked but different things to evaluate.",
        "Cohere’s maintained overview later lists Rerank v3.5 as a model option and records its 4K context. That current catalog is useful context, not proof that a specific December integration used the same endpoint, candidate limit, or operating policy."
      ],
      "bullets": [],
      "source_ids": [
        1,
        2
      ]
    },
    {
      "id": "token-boundary",
      "url": "https://rangoon.ai/insights/archive-cohere-rerank-3-5-december-2024/#token-boundary",
      "heading": "Token limits make document segmentation part of ranking behavior",
      "paragraphs": [
        "When a candidate is longer than the model’s effective input budget, an application must decide what portion reaches the ranker. Segmenting earlier can preserve several local passages, while sending a broad document can retain global context but consume more of the 4,096-token allowance. The v2 move to max_tokens_per_doc exposes that choice at the request boundary. An application migrating an old chunk-count setting cannot reuse the same integer as a token limit without changing how much of each document is examined.",
        "Neither a token limit nor a YAML-formatted semi-structured document guarantees the right ordering. A useful evaluation fixes the candidate generator, corpus version, query set, relevance labels, truncation rule, and ranking metric so a changed model or API parameter has a visible effect."
      ],
      "bullets": [],
      "source_ids": [
        1
      ]
    },
    {
      "id": "measurement-limit",
      "url": "https://rangoon.ai/insights/archive-cohere-rerank-3-5-december-2024/#measurement-limit",
      "heading": "A reranker release is not an end-to-end search result",
      "paragraphs": [
        "Cohere’s release records a dated model and API evolution. It does not disclose a customer’s corpus, access rules, first-stage retriever, latency target, fallback behavior, or relevance labels. Those surrounding choices can outweigh a model change for a real search product.",
        "The narrow historical conclusion is that Cohere introduced Rerank version 3.5 and the stated v2 API changes on December 2. It does not prove a universal relevance gain, a lower cost, or a compliant retrieval workflow for another organization."
      ],
      "bullets": [],
      "source_ids": [
        1,
        2
      ]
    }
  ],
  "project_context": null,
  "related_links": [],
  "permissions_url": "https://rangoon.ai/permissions.txt",
  "content_hash": "sha256:cba7630520cdd86ff95a2eed553c3afdbe2bf4c0338291178ec3ea64159e940f"
}