Last refreshed 2026-05-16. Next refresh: weekly.
Why use Embed English v3.0 on Microsoft Foundry?
Microsoft Foundry offers Embed English v3.0 with pay-as-you-go pricing at $0.10/1M input tokens. Microsoft Foundry is a unified Azure platform-as-a-service offering for enterprise AI operations, model builders, and application development.
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: Cohere-embed-v3-englishCohere-embed-v3-englishRequest example
Cohere-embed-v3-english.Gotchas
- Use provider model ID "Cohere-embed-v3-english", not the LLMReference slug "cohere-embed-english-v3-0".
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.10 |
Capabilities
About Embed English v3.0
English-only embedding model supporting text and image inputs. Produces 1024-dimensional embeddings optimized for semantic search, classification, and clustering. Supports multiple similarity metrics (Cosine, Dot Product, Euclidean Distance).
FAQ
What is the context window for Embed English v3.0 on Microsoft Foundry?
Embed English v3.0 supports a 512 token context window on Microsoft Foundry.
What API model ID do I use for Embed English v3.0 on Microsoft Foundry?
Use the model ID Cohere-embed-v3-english when calling Microsoft Foundry's API.
Who created Embed English v3.0?
Embed English v3.0 was created by Cohere as part of the Embed model family.
Is Embed English v3.0 open source?
Embed English v3.0 is not open source; the seed data lists it as proprietary.