---
title: "Embedding API — Variants, pricing & model skill"
url: "https://runapi.ai/models/embedding.md"
canonical: "https://runapi.ai/models/embedding.md"
locale: "en"
model: "Embedding"
provider: "OpenAI"
modality: "text"
variant_count: 3
price_from_cents: 1
---

# Embedding API

OpenAI text embeddings for semantic search, retrieval, clustering, and ranking workflows.

**Provider:** OpenAI
**Modality:** Text
**Catalog:** 3 variants

OpenAI Embedding models convert text into dense vectors for semantic search, retrieval-augmented generation, clustering, classification, and ranking. The text-embedding-3 family supports efficient production retrieval with optional vector dimensionality control.

## Variants

| Version | Variant | Pricing | Billing | URL |
|---|---|---|---|---|
| text-embedding-3-large | `text-embedding-3-large` | $0.010 | 1K tokens | https://runapi.ai/models/embedding/text-embedding-3-large.md |
| text-embedding-3-small | `text-embedding-3-small` | $0.010 | 1K tokens | https://runapi.ai/models/embedding/text-embedding-3-small.md |
| text-embedding-ada-002 | `text-embedding-ada-002` | $0.010 | 1K tokens | https://runapi.ai/models/embedding/text-embedding-ada-002.md |


## API endpoints

Base URL: `https://runapi.ai`

- `POST /v1/embeddings`

Use the OpenAI or Anthropic SDK with your RunAPI API key. No extra SDK required.

## Context

OpenAI Embedding models expose the standard OpenAI Embeddings API through RunAPI, so vector search and RAG pipelines can use the same RunAPI key as GPT chat and Responses traffic.

## FAQ

### Which variant should I start with?

Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.

### Is there a free tier?

New accounts get free first calls on every model. After that, pay per call.

### Do you stream results?

Where streaming is available, RunAPI streams end-to-end.

### How are failures billed?

Failed generations are not charged.

### Are outputs cached?

Generated outputs are stored and retrievable by task ID. Inputs are not cached.

### Can I use commercially?

Yes — commercial use is included for every variant unless a model license explicitly restricts it, which is called out on the variant page.

### What about rate limits?

Per-key rate limits scale with usage tier. See pricing page for current limits.

### Where can I report issues?

Open an issue on the public GitHub repo or email support.