text-embedding-3-small

Text

Efficient text vectors for production semantic search

Input $0.02 / 1M tokens | Output Free / 1M tokens text-embedding-3-small API reference →

Model health Insufficient data

runapi.ai

# Base URL
https://runapi.ai

# Endpoints
POST /v1/embeddings

curl https://runapi.ai/v1/embeddings \
  -H "Authorization: Bearer $RUNAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "text-embedding-3-small",
  "input": [
    "Embed these support articles and a customer query so I can rank the closest matches."
  ],
  "encoding_format": "float"
}'

from openai import OpenAI

client = OpenAI(
    base_url="https://runapi.ai/v1",
    api_key="your-runapi-key"
)

response = client.chat.completions.create(
    model="text-embedding-3-small",
    messages=[{"role": "user", "content": "Embed these support articles and a customer query so I can rank the closest matches."}]
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://runapi.ai/v1",
  apiKey: "your-runapi-key"
});

const response = await client.chat.completions.create({
  model: "text-embedding-3-small",
  messages: [{ role: "user", content: "Embed these support articles and a customer query so I can rank the closest matches." }]
});

https://runapi.ai 1 endpoint

3 versions available

Playground

Try text-embedding-3-small

Pick any model and generate in seconds.

No models are available right now.

Specifications

Provider	OpenAI
Model ID	text-embedding-3-small
Modality	Text
Task types	Synchronous

API endpoint	/v1/embeddings
Billing unit	1K tokens
Catalog status	Operational

HOW IT WORKS

Use This Model in 3 Steps

Get Your Key

Sign up for free and create an API key for text-embedding-3-small from the dashboard.
Send a Request

POST to /v1/embeddings with the text-embedding-3-small model slug and your parameters.
Get Results

Read the completed text-embedding-3-small response directly from the endpoint.

What this model offers

Endpoint coverage

Exposes 1 public endpoint(s): embedding.

Usage-based billing

Metered by 1K tokens with no subscription requirement.

text-embedding-3-small Pricing

Endpoint

Price

embedding

Input: $0.02 / 1M tokens Output: Free / 1M tokens

API REFERENCE

Endpoint Specification

Endpoint: POST /v1/embeddings
Model ID: text-embedding-3-small
Task Types: embedding

Request parameters

No request parameters are published for this endpoint.

USE CASES

Semantic search

Index documents, FAQs, or product catalogs as vectors and retrieve the most relevant results by meaning instead of keyword match.

RAG pipelines

Embed knowledge-base chunks and feed the closest matches into an LLM prompt for grounded, citation-backed answers.

Clustering & classification

Group support tickets, survey responses, or user feedback by semantic similarity without manual labeling.

FAQ

Frequently asked questions about text-embedding-3-small

How do I select text-embedding-3-small?

Pass the model ID shown in the quickstart.

What's the rate limit on this variant?

Per-key rate limits scale with your usage tier. The pricing page shows current limits. If you need higher throughput, contact support to discuss tier upgrades.

Can I switch variants later?

Yes. Variant is a parameter in the request. Switch by changing the model ID — no code changes, no re-authentication, no separate billing setup. All variants share the same API key and request shape.

Does it stream?

Where streaming is available, RunAPI streams end-to-end. LLM models support token-level streaming. Media models use async task polling or webhook callbacks for result delivery.

Where do I report quality issues?

Open an issue on the public GitHub repo or email support at [email protected]. Include the task ID and model ID so the team can investigate the specific generation.

Do I need a separate provider account?

No. Your RunAPI API key is enough to access this variant and every other model in the catalog. You do not need accounts with the underlying provider.

What dimensions does text-embedding-3-small output?

text-embedding-3-small outputs 1,536 dimensions by default. It supports Matryoshka embeddings, so you can request 256, 512, or 1,024 dimensions to reduce storage cost while retaining most of the retrieval quality.

How does text-embedding-3-small compare to text-embedding-3-large?

text-embedding-3-large has 3,072 dimensions and scores about 2 points higher on the MTEB benchmark, but costs roughly 6.5 times more per million tokens. For most semantic search and RAG use cases, text-embedding-3-small delivers comparable quality at a fraction of the cost.

What is the cost of text-embedding-3-small on RunAPI?

RunAPI charges per embedding call with no subscription or minimum spend. Check the pricing grid on this page for the current per-call rate. Failed requests are never charged.

Can I use batch processing to reduce embedding costs?

Yes. Send multiple texts in a single API call to reduce overhead. RunAPI processes batch embedding requests and returns all vectors in one response, which is more efficient for indexing large document collections.

Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.