Knowledge & Data · Software component
Hosted Embedding API Service
Software componentKnowledge & DataKnowledge & Dataarc:HostedEmbeddingAPIService
An embedding service consumed from a third-party provider's hosted API, billed per token, with the provider operating models and infrastructure.
Responsibility. Returns embeddings for submitted texts from a provider-operated model endpoint.
Also known as: Embedding API, Commercial embedding API
Variant of Embedding Service abstract
When to choose. Choose when building initial development or baseline systems, when no data-sovereignty or air-gap constraint applies, and when per-token API cost is acceptable for the query volume.
Relationships
exposes structural
hosts structural
is invoked by dependency
fails over to control
alternative to variability
Design guidance
- MAY be used for development and baseline measurement before transitioning to self-hosted production embedding.
Quantitative guidance
As stated by the sources; verify before use.
- Per-million-token prices cited: $0.13 (text-embedding-3-large), $0.02 (text-embedding-3-small, 85% cheaper), $0.10 (Cohere embed-english-v3) (Ch6.1).
Classification
- Patterns
- Per-token pay-as-you-go consumptionStart with small/cost-optimized variant for baseline, upgrade selectively
- Technologies
- OpenAI Embeddings APICohere Embed API
- Quality attributes
- Maintainability (ISO/IEC 25010)
- Risks mitigated
- Operational burden of model deployment and GPU infrastructure
Sources
- Ch6.1: T. Nguyen, "Embeddings and RAG Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 6.1. ISBN: 9798244538229.