{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/cohere-rerank-4/","md":"https://postcutoff.com/m/cohere-rerank-4/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"cohere-rerank-4","name":"Cohere Rerank 4 (Pro / Fast)","org":"Cohere","family":"Rerank","released":"2025-12-11","status":"current","type":"embedding","modality_in":["text"],"modality_out":["text"],"open_weights":false,"model_license":"proprietary","context_window":32000,"max_output":null,"knowledge_cutoff":null,"pricing":null,"price_line":"Price not published","access":[{"provider":"Cohere API","model_id":"rerank-v4.0-pro","endpoint":"https://api.cohere.com/v2/rerank","docs":"https://docs.cohere.com/docs/models"},{"provider":"Cohere API (fast)","model_id":"rerank-v4.0-fast","endpoint":"https://api.cohere.com/v2/rerank"},{"provider":"OpenRouter","model_id":"cohere/rerank-4-pro","url":"https://openrouter.ai/cohere/rerank-4-pro"}],"capabilities":[{"name":"32K-context reranking","detail":"Rerank window grew from 4K (v3.5) to 32K tokens, so whole long documents can be scored.","first":false,"discovered":"launch","source":"https://docs.cohere.com/docs/models"},{"name":"Pro / Fast tiers","detail":"Two variants: pro for best accuracy, fast for latency-sensitive search.","first":false,"discovered":"launch","source":"https://docs.cohere.com/docs/models"}],"entry":null,"notes":"Reranker (scores query-document relevance). Previous: rerank-v3.5 (Bedrock cohere.rerank-v3-5:0). Release date from third-party listing; pricing not verified (OpenRouter ~$0.0025/search reported, not checked).","verified":"2026-09-29","body_md":"Second-stage reranking for RAG and enterprise search.\n\n```bash\ncurl https://api.cohere.com/v2/rerank -H \"Authorization: Bearer $CO_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"rerank-v4.0-pro\",\"query\":\"capital of France\",\"documents\":[\"Paris is the capital of France.\",\"Berlin is in Germany.\"]}'\n```\n\nSources: https://docs.cohere.com/docs/models","page_url":"https://postcutoff.com/m/cohere-rerank-4/","standing":{"kind":"embedding","newer_count":4,"newer":[{"id":"embeddinggemma-2","name":"EmbeddingGemma 2","org":"Google DeepMind","released":"2026-10-06","page_url":"https://postcutoff.com/m/embeddinggemma-2/"},{"id":"cohere-embed-v5-fast","name":"Cohere Embed 5 Fast","org":"Cohere","released":"2026-09-30","page_url":"https://postcutoff.com/m/cohere-embed-v5-fast/"},{"id":"cohere-embed-v5-pro","name":"Cohere Embed 5 Pro","org":"Cohere","released":"2026-09-30","page_url":"https://postcutoff.com/m/cohere-embed-v5-pro/"},{"id":"gemini-embedding-2","name":"Gemini Embedding 2","org":"Google DeepMind","released":"2026-04-22","page_url":"https://postcutoff.com/m/gemini-embedding-2/"}],"before":{"id":"cohere-embed-v4","name":"Cohere Embed v4","org":"Cohere","released":"2025-04","page_url":"https://postcutoff.com/m/cohere-embed-v4/"},"after":{"id":"cohere-embed-v5-pro","name":"Cohere Embed 5 Pro","org":"Cohere","released":"2026-09-30","page_url":"https://postcutoff.com/m/cohere-embed-v5-pro/"},"weights":"closed","licence":"proprietary","licence_permissive":false,"summary":"Closed weights; access is hosted only."}}