As of: 2026-11-19 22:11 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/m/cohere-embed-v5-pro/ # Cohere Embed 5 Pro Cohere, Embed family. Status: current. Type: embedding model. Released: 2026-09-30. ## How to call it | Provider | Model id | Endpoint | Docs | |---|---|---|---| | Cohere API | `embed-v5.0-pro` | https://api.cohere.com/v2/embed | https://docs.cohere.com/changelog/embed-v5 | | Microsoft Foundry | | | | | Amazon SageMaker | | | | | Cohere Model Vault | | | | ## Pricing - Input: $0.12 per 1M tokens - Unit as published: per 1M text tokens (images $0.40 per 1M tokens) - Source: https://cohere.com/blog/embed-5 - Last checked: 2026-10-01 ## Specs - Input: text, image - Output: text - Context window: 128,000 tokens - Max output: not published - Open weights: no - Licence: proprietary ## Where it stands - Newer embedding models in the registry since its release: 1: - EmbeddingGemma 2 (2026-10-06) https://postcutoff.com/m/embeddinggemma-2/ - Before it from Cohere: Cohere Rerank 4 (Pro / Fast) (2025-12-11) https://postcutoff.com/m/cohere-rerank-4/ - Closed weights; access is hosted only. ## What stands out - Shared embedding space across tiers: Embed 5 Pro and Fast vectors are interoperable: index with Pro, query with Fast without re-indexing. Source: https://docs.cohere.com/changelog/embed-v5 - Multimodal 128K embeddings: Text, image and fused text+image input, 100+ languages, Matryoshka dims 256-2048. Source: https://docs.cohere.com/changelog/embed-v5 ## Notes Highest-quality tier for offline indexing; ViDoRe V3 85.8 (Cohere). Output is vectors (modality_out text used as placeholder). Bedrock/Foundry model ids not verified. ```bash curl https://api.cohere.com/v2/embed -H "Authorization: Bearer $CO_API_KEY" -H "Content-Type: application/json" \ -d '{"model":"embed-v5.0-pro","input_type":"search_query","embedding_types":["float"],"texts":["hello world"]}' ``` Model page: https://postcutoff.com/m/cohere-embed-v5-pro/