Cohere Embed
CohereCohere’s embedding model line, currently embed-v4.0: a single multimodal model that embeds text, images and mixed text/image payloads such as PDFs into one space. It carries a 128k context, Matryoshka output dimensions of 256, 512, 1024 or 1536, and is sold through Cohere’s Embed endpoint, AWS SageMaker and Bedrock, and Azure AI Foundry.
embed-v4.0 is still the head of the line as of 2026-09-11 — Cohere’s own model table lists it as the latest, with the v3.0 English/multilingual pair below it and nothing newer. No weights are published for any SKU; the private-deployment option is a priced dedicated instance, not a download.
Openness
1 high confidence- weights
- closed(embed-v4.0 is served through the Embed endpoint and cloud marketplaces
- data
- closed(training corpus not released or described)
- code
- closed(no training or inference implementation
- license
- proprietary(hosted API
Embed v4 is API-only; no weights, training data or code are published for any SKU. The pricing page's dedicated-instance tier reads like self-hosting, but it rents a Cohere-managed instance rather than offering a download.
- https://cohere.com/pricing recorded 2026-09-11
Prices Embed 4 as hosted usage and as dedicated instances — 'Embed 4 Small $4.00 hourly / $2,500 monthly per instance', 'Embed 4 Medium $5.00 / $3,250' — which is rented capacity, not a weights license.
- https://docs.cohere.com/docs/cohere-embed recorded 2026-09-11
The Embed model table lists embed-v4.0 as the latest model with a 128k context and Matryoshka dimensions '[256, 512, 1024, 1536 (default)]', reached through the Embed endpoint. No weight download, self-hosted build is offered for it or for any v3.0 SKU. Two Hub repositories do exist under CohereLabs for the v3.0 embed models, but both ship only a config and a tokenizer - no weight file - so neither is a distribution of the model.
Adoption
3 medium confidenceCohere publishes no download or call-volume figure for Embed v4, so adoption is read from its distribution instead: Cohere's own platform, AWS SageMaker and Bedrock, and Azure AI Foundry, where Microsoft sells it directly, the same breadth as cohere-rerank-api.
- https://docs.cohere.com/changelog/embed-multimodal-v4 recorded 2026-09-11
'Embed v4 is available today on the Cohere Platform, AWS Sagemaker, and Azure AI Foundry.' Carries no usage figure.
- https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models recorded 2026-09-11
Azure AI Foundry's models-sold-directly-by-Azure list carries embed-v-4-0, confirming Microsoft resells it.
Capability
4 high confidenceEmbed v4 is Cohere's current model: multilingual, long-context at 128k tokens, and multimodal in one pass. What keeps it short of the top is that the only public head-to-head benchmark is a rival's, placing it behind on RTEB, while Cohere's own state-of-the-art claim carries no published number.
- https://blog.voyageai.com/2026/01/15/voyage-4/ recorded 2026-09-11
Over all 29 RTEB datasets, voyage-4-large surpasses Cohere Embed v4 by an average of 8.20%.
- https://docs.cohere.com/changelog/embed-multimodal-v4 recorded 2026-09-11
'Embed v4 achieves state of the art in the following areas: Text-to-text retrieval, Text-to-image retrieval, Text-to-mixed modality retrieval (from e.g. PDFs)'; 'Context length of 128k'. No numeric result is given.
Verified 2026-09-11