Last refreshed 2026-07-01. Next refresh: weekly.
Why use Cohere Embed v4.0 on Cohere API?
Cohere API offers Cohere Embed v4.0 with competitive pricing. Cohere is a leading enterprise AI company that specializes in developing large language models (LLMs) and Retrieval-Augmented Generation (RAG) capabilities.
Compare Cohere Embed v4.0 across 3 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: embed-v4.0embed-v4.0Request example
embed-v4.0.Gotchas
- Use provider model ID "embed-v4.0", not the LLMReference slug "cohere-embed-v4-0".
Compare Cohere Embed v4.0 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Microsoft Foundry | $0.12 | — |
| Vercel AI Gateway | $0.12 | — |
| Cohere API | — | — |
Capabilities
About Cohere Embed v4.0
Latest multimodal embedding model supporting text, images, and mixed content (e.g., PDFs). Embed v4.0 offers variable embedding dimensions (256, 512, 1024, 1536 default) and supports multiple similarity metrics (Cosine, Dot Product, Euclidean Distance). Ideal for semantic search, classification, and clustering across multimodal data.
FAQ
What is the context window for Cohere Embed v4.0 on Cohere API?
Cohere Embed v4.0 supports a 128k token context window on Cohere API.
How does Cohere API compare to other Cohere Embed v4.0 providers?
Cohere Embed v4.0 is available from 3 providers. The cheapest input pricing is $0.12/1M tokens from Microsoft Foundry.
What API model ID do I use for Cohere Embed v4.0 on Cohere API?
Use the model ID embed-v4.0 when calling Cohere API's API.
Who created Cohere Embed v4.0?
Cohere Embed v4.0 was created by Cohere as part of the Cohere Embed model family.
Is Cohere Embed v4.0 open source?
Cohere Embed v4.0 is not open source; the seed data lists it as proprietary.