AI 模型和平台
Cohere 带来嵌入 5 并重排 5 到 OpenRouter 的统一 API
在 Google 上的首选来源中添加 Unite.AI
Cohere 宣布于2026年11月4日表示其Embed 5和Rerank 5检索模型可在OpenRouter上找到。 现有用户可以使用与其他模型相同的API密钥和信用，不单独使用SDK，账户或账单来称呼它们。
模型涵盖一个检索加载生成的检索阶段，即RAG，管道：嵌入5将文档和查询转换成矢量，对查询进行重新计分5个候选人，OpenRouter上的任何聊天模型都可以生成最终答案。 Cohere还发布了一个Python参考工作流程，涵盖索引，检索，相关性过滤和引用生成。
OpenRouter的Embed 5 Pro上市价格为每百万个文字信使12美元，每百万个图像信使40美元，Embed 5 Fast上市价格为每百万个信使0.08美元。 排名第5位的上市价格为每百万个输入符0.5美元，排名第5位的快速价格为每百万个输入符0.2美元。
OpenRouter推出扩展发行，而不是引入另一个模型生成。 Cohere 推出 2026年9月30日嵌入5级，2026年10月21日嵌入5级；两个家庭都提供Pro级和Fast级。
共享嵌入
中心建筑细节是嵌入5 Pro和Fast共享嵌入空间。 因此，如果双方使用相同的输出维度，可以与Pro编制索引，并与Fast进行查询，而不重建索引。 这把指数化工作与每个问题都要求长期和成本敏感的嵌入分开。
Cohere对40个开发数据集的测试中，对Pro-building指数的正常平均检索质量为98.4，对Fast的询问为98.4，对Fast的询问为96.6，对双方的Pro为100。 OpenRouter工作流程采用Pro-index/Fast-query配对，为离线索引阶段保留Pro.
嵌入5提供了从256到2,048维的6个矢量大小，2,048作为默认。 OpenRouter的例子使用1,024维浮点矢量，因为它的嵌入式API返回浮点；Cohere在此维度上分别推荐int8矢量作为其首选的质量与成本点。 Batching块在索引编制过程中会减少网络往返，但不会减少基于符号的嵌入费。 在线路径使用一个Embed 5快速呼叫，一个Rerank 5呼叫，当上下文在过滤器中幸存下来时，每个提问一个聊天呼叫。
相关性分数控制生成背景
参考管道通过余弦相似性回收20块，随问而送至Rerank 5，将多达5个结果并丢弃分数低于0.3的演示阈值。 重新排位会读取查询和每个候选人一起阅读，而不是仅仅依赖向量接近，可以在语义，关键词或混合搜索后进行操作而无需嵌入5.
Cohere 称 Rerank 5的校准分数在查询和域间保持一致，允许一个阈值来决定哪个上下文到达生成器；其发布文档将0.7的分数描述为一个文档有用概率的70%. Pro的用意是用于推理重的查询和长文件或域特定文件，而Fast则针对大量搜索和反复搜索的agents. 模型支持一个32K-token上下文，可以处理JSON记录或格式化为YAML字符串的表格。
在一代人中，幸存的块成为了编号的来源，指令只从它们中回答并引用它们的内容。 如果没有人清除阈值，工作流程报告说找不到答案并跳过聊天模式调用。 由于Rerank在查询时间读取原始文本，切换reranker版本不需要重新索引或重新嵌入。
示范成果和生产制约因素
Cohere的演示使用虚构的API文档，并询问如何在不休息时间的情况下旋转一个密钥。 Embedding- only reference将正确的旋转 API 密钥文档排在0.522位，之后Webhook在0.337位签名秘密，在0.316位创建 API 密钥。 重新排位后，正确的文件得分为0.808，两者的近比分都跌到了截断点以下。
样本需要Python 3.10或更新，一个OpenRouter API密钥和Python SDK，以及NumPy用于其内膜矢量存储。 生产实施旨在用矢量数据库取代该储存。 OpenRouter的RAG指导提出重新排位为精准度与相对度的选择：当一个广泛的候选人集必须缩小时，它可以改进结果，但新增是API调用，当最小的延迟度是优先时则不太合适。
多式联运检索需要做一些工作。 嵌入5接受图像和PDF页面等混合文本和图像输入，OpenRouter的嵌入API接受图像URL，但Rerank 5只接受文本。 建议的选项是重新对已解析的页面文本或标题进行排序，或者省略对视觉结果进行重新排序。
OpenRouter将Cohere列为Pro模型和直接向其转发请求的独家提供者。 两份清单都指出，欧盟在区域内的路线没有。
OpenRouter的可用性整合了检索堆栈的集成和计费，而其生产经济学仍与架构相关：一次性Pro索引化，反复出现的Fast查询，重新排序和聊天呼叫，以及控制生成背景的相关阈值。 单一的API不会抹去为该堆记录的添加的暂时性，仅文本重排或区域路径限制。
本文由 AI图鉴自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
AI Models & Platforms
Cohere Brings Embed 5 and Rerank 5 to OpenRouter’s Unified API
Add Unite.AI to your preferred sources on Google
Cohere announced on November 4, 2026 that its Embed 5 and Rerank 5 retrieval models are available on OpenRouter. Existing users can call them with the same API key and credits as other models, without separate SDKs, accounts or bills.
The models cover the retrieval stages of a retrieval-augmented generation, or RAG, pipeline: Embed 5 converts documents and queries into vectors, Rerank 5 rescores candidates against the query, and any chat model on OpenRouter can generate the final answer. Cohere also published a Python reference workflow spanning indexing, retrieval, relevance filtering and cited generation.
OpenRouter’s Embed 5 Pro listing prices the model at $0.12 per million text tokens and $0.40 per million image tokens, with Embed 5 Fast listed at $0.08 per million tokens. Its Rerank 5 Pro listing prices that tier at $0.05 per million input tokens and Rerank 5 Fast at $0.02 per million tokens.
The OpenRouter rollout expands distribution rather than introducing another model generation. Cohere introduced Embed 5 on September 30, 2026, and Rerank 5 on October 21, 2026; both families offer Pro and Fast tiers.
Shared Embeddings Split Indexing and Query Costs
The central architectural detail is that Embed 5 Pro and Fast share an embedding space. A corpus can therefore be indexed with Pro and queried with Fast without rebuilding the index, provided both sides use the same output dimensions. That separates indexing work, which runs once per corpus, from the latency- and cost-sensitive embedding call made for every question.
In Cohere’s tests across 40 development datasets, normalized mean retrieval quality was 98.4 for a Pro-built index queried with Fast and 96.6 with Fast on both sides, against 100 for Pro on both sides. The OpenRouter workflow adopts that Pro-index/Fast-query pairing, reserving Pro for the offline indexing stage.
Embed 5 offers six vector sizes from 256 to 2,048 dimensions, with 2,048 as the default. The OpenRouter example uses 1,024-dimensional floating-point vectors because its embeddings API returns floats; Cohere separately recommends int8 vectors at that dimension as its preferred quality-to-cost point. Batching chunks reduces network round trips during indexing but does not reduce token-based embedding charges. The online path uses one Embed 5 Fast call, one Rerank 5 call and, when context survives the filter, one chat call per question.
Relevance Scores Control Generation Context
The reference pipeline retrieves 20 chunks by cosine similarity, sends them with the question to Rerank 5, keeps as many as five results and discards scores below a demonstration threshold of 0.3. Reranking reads the query and each candidate together rather than relying only on vector proximity, and can operate after semantic, keyword or hybrid search without Embed 5.
Cohere says Rerank 5’s calibrated scores remain consistent across queries and domains, allowing one threshold to decide which context reaches a generator; its launch documentation describes a score of 0.7 as a 70% probability that a document is useful. Pro is intended for reasoning-heavy queries and long or domain-specific documents, while Fast targets high-volume search and agents that search repeatedly. The models support a 32K-token context and can process JSON records or tables formatted as YAML strings.
At generation, surviving chunks become numbered sources, with instructions to answer only from them and cite them inline. If none clears the threshold, the workflow reports that it could not find the answer and skips the chat-model call. Because Rerank reads raw text at query time, switching reranker versions requires no re-indexing or re-embedding.
Demonstration Results and Production Constraints
Cohere’s demonstration uses fictional API documentation and asks how to rotate a key without downtime. Embedding-only retrieval ranked the correct Rotating API keys document first at 0.522, followed by Webhook signing secrets at 0.337 and Creating API keys at 0.316. After reranking, the correct document scored 0.808 and both near-matches fell below the cutoff.
The sample requires Python 3.10 or newer, an OpenRouter API key and Python SDK, and NumPy for its in-memory vector store. Production implementations are directed to replace that store with a vector database. OpenRouter’s RAG guidance presents reranking as a precision-versus-latency choice: it can improve results when a broad candidate set must be narrowed, but adds an API call and is less suitable when minimum latency is the priority.
Multimodal retrieval needs a workaround. Embed 5 accepts images and mixed text-and-image inputs such as PDF pages, and OpenRouter’s embeddings API accepts image URLs, but Rerank 5 is text-only. The proposed options are to rerank parsed page text or captions, or omit reranking for visual results.
OpenRouter lists Cohere as the sole provider for both Pro models and forwards requests directly to it. Both listings state that EU in-region routing is unavailable.
The OpenRouter availability consolidates the retrieval stack’s integration and billing, while its production economics remain tied to the architecture: one-time Pro indexing, recurring Fast query, rerank and chat calls, and the relevance threshold that controls generation context. The single API does not erase the added latency, text-only reranking or regional-routing constraints documented for that stack.
Auto-fetched and translated by AI Atlas. All rights belong to the original author.