How to beginner · 3 min read

OpenAI embeddings cost per token

Quick answer

OpenAI charges for embeddings based on input tokens, typically at a rate of $0.0004 per 1,000 tokens for the text-embedding-3-small model. This means each token costs approximately $0.0000004, so you can estimate your usage cost by counting tokens sent to the embeddings endpoint.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install openai>=1.0

Setup

Install the official OpenAI Python SDK and set your API key as an environment variable to access the embeddings API.

bash

pip install openai>=1.0

Step by step

Use the OpenAI SDK to create embeddings and understand token usage for cost estimation.

python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

text = "OpenAI embeddings cost per token"
response = client.embeddings.create(
    model="text-embedding-3-small",
    input=text
)

embedding_vector = response.data[0].embedding
print(f"Embedding vector length: {len(embedding_vector)}")

# Example token count and cost calculation
# Assume token count for input text is 8 tokens
tokens_used = 8
cost_per_1000_tokens = 0.0004  # USD
cost = (tokens_used / 1000) * cost_per_1000_tokens
print(f"Estimated cost for {tokens_used} tokens: ${cost:.8f}")

output

Embedding vector length: 384
Estimated cost for 8 tokens: $0.00000320

Common variations

You can use different embedding models with varying costs and token limits. Async calls and batch inputs are also supported for efficiency.

python

import asyncio
import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

async def create_embeddings_async(texts):
    response = await client.embeddings.acreate(
        model="text-embedding-3-small",
        input=texts
    )
    return response.data

texts = ["Hello world", "OpenAI embeddings"]
embeddings = asyncio.run(create_embeddings_async(texts))
for i, emb in enumerate(embeddings):
    print(f"Embedding {i} length: {len(emb.embedding)}")

output

Embedding 0 length: 384
Embedding 1 length: 384

Troubleshooting

If you get authentication errors, verify your OPENAI_API_KEY environment variable is set correctly.
For token counting, use OpenAI's tokenizer tools or third-party libraries to avoid underestimating costs.
Check model availability and pricing updates on OpenAI's official pricing page.

✅

Key Takeaways

OpenAI embeddings cost $0.0004 per 1,000 tokens for text-embedding-3-small as of 2026-04.
Calculate cost by counting input tokens and multiplying by the per-token rate.
Use official SDK methods to create embeddings and monitor token usage for budgeting.

Verified 2026-04 · text-embedding-3-small

Verify ↗