OpenAI · Embeddings
Text Embeddings API price
OpenAI’s Text Embeddings through one prepaid, OpenAI-compatible key: $0.02 per 1M tokens, the provider’s list price with nothing added per request.
Text Embeddings price
- Price
- $0.02per 1M tokens
OpenAI’s list price, in US dollars. Tokens.Pay adds a 5% fee (minimum $0.79) when you add credit, never per request.
What Text Embeddings is good at
Search, clustering and retrieval vectors.
In short: search, clustering and retrieval.
Embeddings model, called at /v1/embeddings. Listed under embeddings.
Text Embeddings endpoint and id
- Provider
- OpenAI
- Type
- Embeddings
- Endpoint
/v1/embeddings- Model id
text-embedding-3-small
What Text Embeddings costs per request
The list price, multiplied out.
| Tokens, in millions | Cost |
|---|---|
| 1 | $0.0200 |
| 10 | $0.2000 |
| 100 | $2.00 |
At $0.02 per 1M tokens, OpenAI’s list price.
Text Embeddings cost calculator
Set how much you need. The provider bills per unit; this is the arithmetic.
Call Text Embeddings with the OpenAI SDK
Base URL https://api.airuntime.dev/v1, your key as the bearer token, and model set to text-embedding-3-small.
curl
curl https://api.airuntime.dev/v1/embeddings \
-H "Authorization: Bearer $TOKENS_PAY_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "text-embedding-3-small", "input": "Prepaid credit for AI models"}'Python
from openai import OpenAI
import os
client = OpenAI(base_url="https://api.airuntime.dev/v1", api_key=os.environ["TOKENS_PAY_KEY"])
result = client.embeddings.create(model="text-embedding-3-small", input="Prepaid credit for AI models")
print(len(result.data[0].embedding))Node
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.airuntime.dev/v1", apiKey: process.env.TOKENS_PAY_KEY });
const result = await client.embeddings.create({ model: "text-embedding-3-small", input: "Prepaid credit for AI models" });
console.log(result.data[0].embedding.length);Who processes Text Embeddings requests
Your code calls AI Runtime directly. It forwards the request to the provider and keeps only the bill.
Processing and storage
- Model provider
- OpenAI · data terms
- Gateway
- AI Runtime, AWS us-east-1
Not stored by Tokens.Pay or AI Runtime. Prompts and outputs exist in memory only while the request runs; we keep the billing record. The provider processes the request under its own terms. Zero data retention, exactly
Text Embeddings API questions
How much does the Text Embeddings API cost?
$0.02 per 1M tokens, OpenAI’s list price. Tokens.Pay adds nothing per request; a 5% fee (minimum $0.79) applies when you add credit.
What is the model id for Text Embeddings?
Send model "text-embedding-3-small" to https://api.airuntime.dev/v1/embeddings with your Tokens.Pay key as the bearer token. Any OpenAI-compatible SDK works.
Does Tokens.Pay store my Text Embeddings prompts?
No. AI Runtime, the gateway your key calls, keeps prompts and outputs in memory only while the request runs and stores just the billing record. The request is processed by OpenAI, under the provider’s own API data terms.
Add credit, then call Text Embeddings.
From $5, plus a 5% top-up fee (minimum $0.79). No subscription; paid credit never expires.
Add credit