How do I generate embeddings?

POST to /v1/embeddings with a model slug and your input text. You get back vectors, using your existing OpenAI-compatible code with a changed base URL and key.

What are embeddings used for?

Semantic search (ranking by meaning, not keywords), RAG pipelines that ground LLM answers in your own data, and clustering or de-duplicating large text collections.

Per token, pay-per-use from your credit balance, with no subscription.

Embedding Model APIs

Generate vector embeddings for semantic search, retrieval-augmented generation, and clustering through one OpenAI-compatible API. ApexApi serves embedding models behind the same key and credit balance as the rest of the catalog, so you can build retrieval without a separate integration.

Start free Read the quickstart

0 Embeddings models on ApexApi

Model	Details	Price /1M tokens

Why build on ApexApi

One API, every model

OpenAI-compatible. Swap the base URL and key, keep your code. Call 14+ providers and hundreds of models through a single integration.

Smart routing & failover

Per-model provider chains with automatic failover. If one provider degrades, requests route to the next. Your app stays up.

Pay-per-use, no lock-in

Buy credits, pay only for what you call. No subscriptions, no minimums. Switch models anytime with a single string change.

Frequently asked questions

How do I generate embeddings?: POST to /v1/embeddings with a model slug and your input text. You get back vectors, using your existing OpenAI-compatible code with a changed base URL and key.
What are embeddings used for?: Semantic search (ranking by meaning, not keywords), RAG pipelines that ground LLM answers in your own data, and clustering or de-duplicating large text collections.
How is it billed?: Per token, pay-per-use from your credit balance, with no subscription.