{"version":1,"type":"story","url":"https://digestai.news/story/cohere-launches-embed-5-pro-and-fast-for-enterprise-search-and-agents","json":"https://digestai.news/story/cohere-launches-embed-5-pro-and-fast-for-enterprise-search-and-agents.json","markdown":"https://digestai.news/story/cohere-launches-embed-5-pro-and-fast-for-enterprise-search-and-agents.md","slug":"cohere-launches-embed-5-pro-and-fast-for-enterprise-search-and-agents","headline":"Cohere launches Embed 5 Pro and Fast for enterprise search and agents","summary":"Cohere released Embed 5 on September 30, a multimodal embedding model family split into two tiers: **Embed 5 Pro** (optimized for retrieval quality) and **Embed 5 Fast** (optimized for speed and cost). Both support text, images, and fused text-image inputs, cover 128K tokens, and 100+ languages. A key feature is their shared embedding space—users can index with Pro and query with Fast without re-indexing, provided dimensions match.\n\nThe models are now generally available via Cohere’s API, Model Vault, Microsoft Foundry, and Amazon SageMaker. Benchmarks show Embed 5 Pro scoring **85.8 on ViDoRe V3**, ahead of Voyage 4 Large (83.7) and Gemini Embedding 2 (83.2). Embed 5 Fast costs **$0.08 per 1M text tokens**, while Pro costs **$0.12**, with image inputs priced at **$0.40 per 1M tokens**. Fast processes **377.3 documents per second**, nearly **2.4x faster** than Pro. Storage efficiency is also highlighted: 256-dim binary vectors use just **32 bytes**, a **256x reduction** compared to 2048-dim float32 vectors.","keyPoints":["Embed 5 Pro scores 85.8 on ViDoRe V3, outperforming Voyage 4 Large and Gemini Embedding 2","Embed 5 Fast costs $0.08 per 1M text tokens and processes 377.3 docs/sec, 2.4x faster than Pro","Pro and Fast share one embedding space: index with Pro, query with Fast for speed without re-indexing"],"whyItMatters":"Embed 5’s shared embedding space and tiered performance let enterprises balance cost, speed, and accuracy for agentic retrieval and RAG, reducing storage needs by up to 256x.","category":{"slug":"enterprise","name":"Enterprise & Industry","url":"https://digestai.news/category/enterprise"},"entities":{"companies":["Cohere","Microsoft","Amazon","Voyage AI","Google","OpenAI"],"models":["Embed 5 Pro","Embed 5 Fast","Voyage 4 Large","Gemini Embedding 2","OpenAI text-embedding-3-large"],"people":[]},"firstPublishedAt":"2026-10-01T17:13:12Z","updatedAt":"2026-10-01T17:13:12Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"MarkTechPost","title":"Cohere Releases Embed 5: How It Compares to Voyage 4 Large, Gemini Embedding 2, and OpenAI","url":"https://marktechpost.com/2026/10/01/cohere-releases-embed-5","publishedAt":"2026-10-01T17:13:12Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":{"title":"Enterprise AI Search Infrastructure Accelerates","url":"https://digestai.news/thread/conde-nast-cuts-video-search-time-from-250-minutes-to-2-minutes-using-amazon","storyCount":2},"cite":{"text":"Digest AI, \"Cohere launches Embed 5 Pro and Fast for enterprise search and agents\", 1 October 2026, https://digestai.news/story/cohere-launches-embed-5-pro-and-fast-for-enterprise-search-and-agents","publisher":"Digest AI","title":"Cohere launches Embed 5 Pro and Fast for enterprise search and agents","datePublished":"2026-10-01T17:13:12Z","url":"https://digestai.news/story/cohere-launches-embed-5-pro-and-fast-for-enterprise-search-and-agents"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}