{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"cohere-rerank-3","slug":"cohere-rerank-3","name":"Cohere Rerank 3","type":"api","url":"https://cohere.com/rerank","page_url":"https://unfragile.ai/cohere-rerank-3","categories":["rag-knowledge","deployment-infra","testing-quality"],"tags":[],"pricing":{"model":"free","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"cohere-rerank-3__cap_0","uri":"capability://search.retrieval.cross.lingual.document.reranking.with.relevance.scoring","name":"cross-lingual document reranking with relevance scoring","description":"Reranks candidate documents against a query using a cross-encoder architecture that jointly encodes query-document pairs through cross-attention mechanisms, producing normalized relevance scores. Supports 100+ languages without language-specific model variants, enabling multilingual RAG pipelines to improve retrieval precision by 20-40% when integrated downstream of initial retrieval. Processes documents up to 4,096 tokens and returns scored rankings suitable for context selection in LLM prompts.","intents":["I need to improve search relevance in my RAG system without retraining my retriever","I want to filter and rank retrieved documents by relevance before passing them to an LLM","I'm building a multilingual search system and need language-agnostic ranking","I need to reduce hallucinations in RAG by ensuring only the most relevant documents reach the LLM context window"],"best_for":["teams building production RAG systems requiring precision over recall","enterprises with multilingual document collections (100+ languages)","developers integrating reranking into existing BM25, vector, or hybrid search backends","AI agent builders filtering candidate documents before LLM reasoning steps"],"limitations":["Hard constraint: 4,096 tokens per document — longer documents are truncated, potentially losing relevance signals","Reranking-only model: requires pre-retrieved candidate set; cannot perform initial retrieval independently","Unknown query token limit and maximum batch size per request — may require pagination for large document sets","Cross-lingual performance not validated per language — 100+ language claim lacks per-language benchmark data","Score normalization and range unknown — unclear if scores are 0-1, 0-100, or unbounded, affecting threshold-based filtering","Latency per document and throughput unknown — 'real-time' claim lacks quantified benchmarks, may not scale to thousands of documents per query"],"requires":["Cohere API key (free trial key for development, production key for commercial use)","Pre-retrieved candidate documents from any search backend (BM25, vector embeddings, hybrid)","HTTP client or Cohere SDK (Python, Node.js, Go, Java supported)","Query text and list of candidate documents in plaintext or semi-structured format (emails, tables, JSON, code)"],"input_types":["query (text, language-agnostic)","documents (plaintext, emails, tables, JSON, code — up to 4,096 tokens each)","document metadata (optional, not used in ranking)"],"output_types":["relevance scores (format and range unknown — likely 0-1 or 0-100)","ranked document indices or IDs","optionally: original document text with scores for downstream processing"],"categories":["search-retrieval","memory-knowledge","rag-optimization"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"cohere-rerank-3__cap_1","uri":"capability://search.retrieval.multi.backend.retrieval.pipeline.integration","name":"multi-backend retrieval pipeline integration","description":"Integrates seamlessly into existing search infrastructure by accepting pre-retrieved candidate documents from any backend (BM25, vector similarity, hybrid search) and returning reranked results without modifying the underlying retriever. Acts as a precision filter layer that can be inserted post-retrieval in RAG pipelines, search APIs, or agent context-selection workflows. Supports batch reranking of multiple document sets per query.","intents":["I want to add reranking to my existing Elasticsearch or Solr BM25 search without changing my retriever","I need to improve vector search results by reranking embeddings-based candidates","I'm combining BM25 and vector search (hybrid) and want to rerank the merged results","I want to A/B test reranking impact on my search system without production downtime"],"best_for":["teams with existing search infrastructure (Elasticsearch, Solr, Pinecone, Weaviate, Milvus) seeking precision improvements","hybrid search implementations combining lexical and semantic retrieval","enterprises with established RAG pipelines wanting to add a precision layer","developers building search-as-a-service platforms with pluggable ranking components"],"limitations":["Requires pre-retrieved candidate set — cannot replace initial retrieval, only reorder results","Unknown maximum batch size per request — may require pagination for large result sets (e.g., reranking 1000+ documents per query)","Latency overhead unknown — adding reranking step may increase end-to-end query latency; no benchmarks provided for typical document counts","No built-in caching or memoization — repeated queries with identical documents will be reranked again, increasing API costs","Integration examples limited — no reference implementations for popular search frameworks (Elasticsearch, OpenSearch, Milvus)"],"requires":["Cohere API key (production key for commercial use)","HTTP client or Cohere SDK","Pre-retrieved candidate documents from any search backend","Query text corresponding to the retrieved documents"],"input_types":["query (text)","candidate documents (list of texts, each up to 4,096 tokens)","optional: document IDs or metadata for tracking results"],"output_types":["reranked document list with relevance scores","document indices or IDs in new rank order","scores suitable for threshold-based filtering or confidence ranking"],"categories":["search-retrieval","tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"cohere-rerank-3__cap_10","uri":"capability://tool.use.integration.model.versioning.with.performance.improvements","name":"model versioning with performance improvements","description":"Cohere maintains multiple reranking model versions (Rerank 3, Rerank 3.5, Rerank 4 Fast, Rerank 4 Pro) with incremental performance improvements. Rerank 3 is superseded by newer versions (Rerank 4 announced December 11, 2025) offering better accuracy and speed. API supports version selection, enabling gradual migration to newer models or A/B testing of versions.","intents":["Upgrade to newer reranking models as they become available","A/B test different model versions to measure quality improvements","Balance accuracy vs. latency by choosing appropriate model version","Gradually migrate from older to newer models without disrupting production"],"best_for":["Production systems requiring continuous quality improvements","Teams conducting A/B tests of reranking quality","Applications with strict latency requirements (may benefit from Fast variant)","Organizations seeking best-in-class reranking accuracy (Pro variant)"],"limitations":["Model version selection mechanism unknown — unclear how to specify version in API calls","Performance differences between versions unknown — no published benchmarks comparing Rerank 3, 3.5, 4 Fast, 4 Pro","Pricing differences between versions unknown — unclear if newer versions cost more","Deprecation timeline unknown — unclear when Rerank 3 will be sunset","Migration path unclear — no guidance on upgrading existing deployments to newer versions"],"requires":["Cohere API key","Knowledge of available model versions and their characteristics","Integration code to specify model version in API calls (if supported)"],"input_types":["same as base reranking capability"],"output_types":["same as base reranking capability"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"cohere-rerank-3__cap_2","uri":"capability://search.retrieval.long.document.relevance.assessment.with.token.aware.truncation","name":"long-document relevance assessment with token-aware truncation","description":"Processes documents up to 4,096 tokens per document, automatically handling truncation for longer texts while preserving relevance signals. Uses cross-encoder attention to assess query-document relevance across long-form content including emails, tables, JSON, and code. Designed for enterprise document types where relevance may span multiple sections or require understanding of document structure.","intents":["I need to rank long emails or documents (>2000 tokens) by relevance to a query","I want to extract the most relevant documents from a corpus of research papers or technical documentation","I'm building a workplace search system (email, Slack, documents) and need to rank mixed content types","I need to filter long-form content before passing to an LLM to avoid context window overflow"],"best_for":["enterprise search systems handling emails, PDFs, and long-form documents","workplace search platforms (Cohere North, Compass) with mixed content types","RAG systems over technical documentation, research papers, or code repositories","teams processing semi-structured data (JSON, tables, code) requiring relevance ranking"],"limitations":["Hard 4,096-token limit per document — documents exceeding this are truncated, potentially losing tail-end relevance signals","Truncation strategy unknown — unclear if truncation prioritizes document beginning, end, or uses intelligent selection","Performance degradation near token limit unknown — no benchmarks for documents at 3,000+ tokens vs. shorter documents","No document chunking or sliding-window support — long documents must be pre-chunked before reranking","Behavior with very short documents (< 50 tokens) unknown — may produce unreliable scores for minimal content"],"requires":["Cohere API key","HTTP client or SDK","Documents pre-tokenized or raw text (tokenization handled by API)","Query text"],"input_types":["long-form text (emails, PDFs, documentation, code, tables, JSON)","semi-structured data (emails with headers, tables with rows, JSON with nested fields)","documents up to 4,096 tokens"],"output_types":["relevance scores per document","ranked document list","scores indicating confidence in relevance assessment"],"categories":["search-retrieval","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"cohere-rerank-3__cap_3","uri":"capability://search.retrieval.multilingual.relevance.ranking.without.language.specific.models","name":"multilingual relevance ranking without language-specific models","description":"Ranks documents in 100+ languages using a single unified cross-encoder model without requiring language detection or language-specific model switching. Processes queries and documents in different languages within the same request, enabling cross-lingual relevance assessment. Designed for global enterprises and multilingual document collections without the overhead of maintaining separate ranking models per language.","intents":["I have a multilingual document corpus (English, Spanish, French, Chinese, etc.) and need to rank results for queries in any language","I want to build a global search system that handles mixed-language queries and documents without language detection","I'm building a multilingual RAG system and need language-agnostic document ranking","I need to rank documents where query and documents may be in different languages"],"best_for":["global enterprises with multilingual document collections","international SaaS platforms requiring language-agnostic search","multilingual RAG systems serving users across regions","teams without language detection infrastructure or language-specific model management"],"limitations":["100+ language support claimed but not validated — no per-language performance benchmarks or language list provided","Cross-lingual performance unknown — unclear if ranking quality degrades for language pairs with limited training data","No language-specific tuning available — single model may not optimize for language-specific ranking preferences","Language detection not performed — if query and documents are in different languages, behavior is undefined","No language-specific score calibration — scores may not be comparable across languages, affecting threshold-based filtering"],"requires":["Cohere API key","HTTP client or SDK","Documents and queries in any of 100+ supported languages (language list not provided)","UTF-8 encoding for non-Latin scripts"],"input_types":["query in any supported language","documents in any supported language (same or different from query)","mixed-language document sets"],"output_types":["relevance scores (language-agnostic)","ranked document list","scores comparable across languages (assumption, not verified)"],"categories":["search-retrieval","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"cohere-rerank-3__cap_4","uri":"capability://memory.knowledge.rag.context.filtering.and.precision.optimization","name":"rag context filtering and precision optimization","description":"Filters and reranks retrieved documents before passing to LLM context windows, ensuring only the most relevant documents are included in prompts. Reduces hallucinations and improves answer quality by removing low-relevance documents that could introduce noise or conflicting information. Integrates into RAG pipelines as a precision layer between retrieval and LLM generation, with scores enabling threshold-based filtering for context window constraints.","intents":["I want to reduce hallucinations in my RAG system by filtering out low-relevance documents before LLM processing","I need to fit more relevant documents into my LLM's context window by removing noise","I'm building an AI agent that needs to select the most relevant documents for reasoning steps","I want to improve answer quality in my RAG system by ensuring only high-confidence documents reach the LLM"],"best_for":["RAG systems prioritizing answer quality over recall","LLM applications with limited context windows (e.g., mobile, edge deployments)","AI agents requiring high-confidence context for reasoning steps","enterprise QA systems where hallucination reduction is critical"],"limitations":["Score range and normalization unknown — unclear how to set thresholds for filtering (e.g., 'keep documents with score > 0.7')","Optimal threshold selection not documented — no guidance on balancing precision vs. recall for different use cases","Latency overhead not quantified — adding reranking step increases end-to-end latency; impact on real-time systems unknown","No built-in context window management — developers must manually manage document count/tokens after reranking","Hallucination reduction not quantified — '20-40% improvement' claim refers to ranking quality, not LLM hallucination rates"],"requires":["Cohere API key","HTTP client or SDK","Retrieved document set from initial retrieval step","Query text","LLM integration (e.g., LangChain, LlamaIndex) for context passing"],"input_types":["query (text)","retrieved documents (list of texts, each up to 4,096 tokens)","optional: document metadata or source information"],"output_types":["relevance scores per document","filtered document list (optionally: top-k documents)","ranked documents suitable for LLM context construction"],"categories":["memory-knowledge","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"cohere-rerank-3__cap_5","uri":"capability://tool.use.integration.api.based.inference.with.cloud.and.private.deployment.options","name":"api-based inference with cloud and private deployment options","description":"Provides reranking via REST API endpoint (`/rerank` v2 API) with cloud-hosted inference on Cohere's infrastructure, Azure AI integration, or private VPC/on-premises deployment through Model Vault. Supports trial API keys (free, rate-limited, development-only) and production API keys (paid, commercial-grade). Enables flexible deployment models from rapid prototyping to enterprise-grade private inference without managing GPU infrastructure.","intents":["I want to quickly prototype a RAG system with reranking without setting up infrastructure","I need to deploy reranking in a private VPC for data residency or compliance requirements","I'm building a SaaS product and need scalable, managed reranking inference","I want to use Cohere Rerank on Azure AI for enterprise integration"],"best_for":["startups and teams prototyping RAG systems (free trial tier)","enterprises requiring private deployment for data residency (VPC, on-premises)","SaaS platforms needing managed, scalable inference without GPU management","Azure customers seeking native integration with Azure AI services"],"limitations":["Trial API key explicitly prohibited for production/commercial use — requires upgrade to production key","Rate limits on trial key unknown — may throttle development workflows","Production pricing unknown for cloud API — only Model Vault pricing provided ($5/hour or $3,250/month per instance)","Latency and throughput unknown — no benchmarks for request/response times or documents-per-second capacity","Private deployment requires Model Vault subscription — no self-hosted or downloadable model weights mentioned","Azure integration details sparse — unclear if feature parity with Cohere API or limited functionality"],"requires":["Cohere API key (trial for development, production for commercial use)","HTTP client or Cohere SDK (Python, Node.js, Go, Java)","Network access to Cohere API endpoint or Azure AI endpoint","For private deployment: Model Vault subscription and VPC/on-premises infrastructure"],"input_types":["HTTP POST request with query and documents","JSON payload (format not fully specified)"],"output_types":["HTTP JSON response with relevance scores","document rankings with scores"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"cohere-rerank-3__cap_6","uri":"capability://search.retrieval.batch.document.reranking.with.multi.query.support","name":"batch document reranking with multi-query support","description":"Processes multiple documents per query in a single API request, enabling batch reranking of large candidate sets without per-document API calls. Supports reranking multiple queries with their respective document sets in a single batch operation. Reduces API overhead and latency compared to sequential per-document ranking, suitable for bulk processing and high-throughput RAG pipelines.","intents":["I need to rerank 100+ documents per query efficiently without making 100 API calls","I want to batch-process multiple queries with their retrieved documents in one request","I'm building a high-throughput search system and need to minimize API latency overhead","I need to rerank large document collections (e.g., 1000+ documents) for a single query"],"best_for":["high-throughput RAG systems processing many queries per second","batch processing workflows (e.g., nightly reranking of search indices)","teams optimizing API costs by batching requests","search systems with large candidate sets per query (100+ documents)"],"limitations":["Maximum batch size unknown — no documentation on request size limits, document count per query, or total payload limits","Batch processing latency unknown — unclear if batch requests are faster than sequential calls or if latency scales linearly with document count","No guidance on batch size optimization — developers must experiment to find optimal batch sizes for their use case","Batch error handling unknown — unclear how partial failures are handled (e.g., one document fails, others succeed)","No streaming or progressive results — must wait for entire batch to complete before receiving results"],"requires":["Cohere API key","HTTP client or SDK supporting batch requests","Multiple documents per query (exact batch size limits unknown)"],"input_types":["batch request with multiple queries and document sets","JSON payload with query-document pairs"],"output_types":["batch response with relevance scores for all documents","ranked document lists per query"],"categories":["search-retrieval","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"cohere-rerank-3__cap_7","uri":"capability://search.retrieval.relevance.scoring.with.threshold.based.filtering","name":"relevance scoring with threshold-based filtering","description":"Returns normalized relevance scores for each document that enable threshold-based filtering and confidence-based ranking. Scores can be used to select top-k documents, filter low-confidence results, or implement dynamic context window management based on relevance thresholds. Supports downstream filtering logic in RAG pipelines without requiring additional ranking steps.","intents":["I want to filter documents by a relevance threshold (e.g., keep only documents with score > 0.7)","I need to select the top-k most relevant documents from a large set","I want to implement dynamic context window management based on document relevance scores","I need to rank documents by confidence for downstream processing or user presentation"],"best_for":["RAG systems implementing threshold-based context filtering","search applications requiring confidence-based ranking","teams building dynamic context window management","applications needing to balance precision vs. recall through score thresholds"],"limitations":["Score range and normalization unknown — unclear if scores are 0-1, 0-100, or unbounded, making threshold selection difficult","No guidance on threshold selection — no documentation on optimal thresholds for different use cases or domains","Score interpretation unclear — unknown if scores are probabilities, confidence measures, or relative rankings","Threshold portability unknown — unclear if thresholds trained on one domain transfer to other domains","No built-in filtering utilities — developers must implement their own threshold logic and filtering"],"requires":["Cohere API key","HTTP client or SDK","Query and documents for reranking","Downstream filtering logic (custom implementation required)"],"input_types":["query (text)","documents (list of texts)"],"output_types":["relevance scores per document (format and range unknown)","optionally: ranked document list with scores"],"categories":["search-retrieval","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"cohere-rerank-3__cap_8","uri":"capability://search.retrieval.enterprise.workplace.search.integration","name":"enterprise workplace search integration","description":"Designed for enterprise workplace search platforms (Cohere North, Compass) that rank emails, documents, Slack messages, and other workplace content. Handles semi-structured data types common in enterprise environments (emails with headers, threaded conversations, tables, JSON metadata). Integrates with workplace search backends to improve relevance of employee-facing search results.","intents":["I'm building an enterprise search system for emails, documents, and Slack and need to improve result relevance","I want to rank workplace content (emails, documents, conversations) by relevance to employee queries","I'm implementing a workplace search product and need a reranking layer for mixed content types","I need to improve search quality for internal knowledge bases and documentation"],"best_for":["enterprises building internal search platforms (email, documents, Slack, Teams)","workplace search products (Cohere North, Compass, similar platforms)","teams implementing knowledge base search for internal documentation","organizations requiring privacy-preserving search (on-premises or VPC deployment)"],"limitations":["Workplace-specific optimizations unknown — unclear how ranking differs from generic document ranking","Email/conversation handling not documented — unclear how threaded emails or multi-turn conversations are processed","Metadata utilization unknown — unclear if email headers, sender information, or timestamps influence ranking","Privacy/compliance features not mentioned — no documentation on data retention, encryption, or compliance certifications","Integration with workplace platforms not documented — no reference implementations for Slack, Teams, Gmail, etc."],"requires":["Cohere API key (production key for commercial use)","HTTP client or SDK","Workplace content (emails, documents, messages) pre-retrieved from workplace systems","Query text from employees"],"input_types":["workplace content (emails, documents, Slack messages, Teams chats, etc.)","semi-structured data (emails with headers, threaded conversations, tables, JSON)","query text from employees"],"output_types":["relevance scores per document","ranked workplace content","scores suitable for search result presentation"],"categories":["search-retrieval","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"cohere-rerank-3__cap_9","uri":"capability://tool.use.integration.azure.ai.platform.integration","name":"azure ai platform integration","description":"Available as managed service on Microsoft Azure AI platform (announced July 24, 2024), enabling deployment within Azure ecosystem. Integrates with Azure Cognitive Search, Azure OpenAI, and other Azure AI services. Maintains same API interface as Cohere cloud, enabling code portability across cloud providers.","intents":["Deploy reranking within Azure ecosystem for organizations standardized on Azure","Integrate reranking with Azure Cognitive Search and Azure OpenAI","Leverage Azure billing and identity management for reranking","Avoid multi-cloud complexity by keeping all services within Azure"],"best_for":["Enterprises standardized on Microsoft Azure","Organizations with Azure Cognitive Search deployments","Teams using Azure OpenAI for LLM inference","Deployments requiring Azure billing and compliance certifications"],"limitations":["Azure-specific deployment details unknown — pricing, SLA, and integration points not documented in provided materials","Requires Azure account and familiarity with Azure AI services","Unclear whether Azure deployment supports private VPC or on-premises options","No published comparison of Azure vs. Cohere cloud pricing or performance"],"requires":["Microsoft Azure account","Azure AI platform access","Integration with Azure Cognitive Search or other Azure AI services (optional)"],"input_types":["same as Cohere cloud API"],"output_types":["same as Cohere cloud API"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"cohere-rerank-3__headline","uri":"capability://search.retrieval.reranking.model.for.improved.search.relevance","name":"reranking model for improved search relevance","description":"Cohere Rerank 3 is an advanced reranking API that enhances search results by re-scoring documents based on their relevance to a query, achieving significant improvements in search quality for production RAG systems.","intents":["best reranking API","reranking model for improving search relevance","API for document scoring","how to enhance search quality with AI","best tools for production RAG systems"],"best_for":["production RAG systems","high-precision search applications"],"limitations":["maximum input size of 4096 tokens"],"requires":["API key for access"],"input_types":["query and list of documents"],"output_types":["relevance scores"],"categories":["search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":60,"verified":false,"data_access_risk":"high","permissions":["Cohere API key (free trial key for development, production key for commercial use)","Pre-retrieved candidate documents from any search backend (BM25, vector embeddings, hybrid)","HTTP client or Cohere SDK (Python, Node.js, Go, Java supported)","Query text and list of candidate documents in plaintext or semi-structured format (emails, tables, JSON, code)","Cohere API key (production key for commercial use)","HTTP client or Cohere SDK","Pre-retrieved candidate documents from any search backend","Query text corresponding to the retrieved documents","Cohere API key","Knowledge of available model versions and their characteristics"],"failure_modes":["Hard constraint: 4,096 tokens per document — longer documents are truncated, potentially losing relevance signals","Reranking-only model: requires pre-retrieved candidate set; cannot perform initial retrieval independently","Unknown query token limit and maximum batch size per request — may require pagination for large document sets","Cross-lingual performance not validated per language — 100+ language claim lacks per-language benchmark data","Score normalization and range unknown — unclear if scores are 0-1, 0-100, or unbounded, affecting threshold-based filtering","Latency per document and throughput unknown — 'real-time' claim lacks quantified benchmarks, may not scale to thousands of documents per query","Requires pre-retrieved candidate set — cannot replace initial retrieval, only reorder results","Unknown maximum batch size per request — may require pagination for large result sets (e.g., reranking 1000+ documents per query)","Latency overhead unknown — adding reranking step may increase end-to-end query latency; no benchmarks provided for typical document counts","No built-in caching or memoization — repeated queries with identical documents will be reranked again, increasing API costs","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.7,"quality":0.9,"ecosystem":0.35,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.28,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:21.548Z","last_scraped_at":null,"last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=cohere-rerank-3","compare_url":"https://unfragile.ai/compare?artifact=cohere-rerank-3"}},"signature":"J8B86QEfWaJ+fHD+Q9STSpwZfZknIeOwQzmIHel0KzS2eRDJ2c3t0K3PwdotQymLwJXJ5ICxPeBwqGzpKHhRDQ==","signedAt":"2026-06-20T19:05:17.516Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/cohere-rerank-3","artifact":"https://unfragile.ai/cohere-rerank-3","verify":"https://unfragile.ai/api/v1/verify?slug=cohere-rerank-3","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}