Skip to content

Model detail

text-embedding-3-small

Provided by OpenAI
Pay-as-you-go

text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.

Model specs

Context length
8.191K
Max output
I/O modalities
Text
Released
2025-10

02

API endpoints

One MixRoute gateway, OpenAI-compatible

  • OpenAI-compatible /v1/chat/completions POST

03

Pricing

Flat rate, unit: /1M Tokens

Input

$0.0200 /1M Tokens

Completion

$0.0200 /1M Tokens

05

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Efficient embedding model for cost-sensitive workloads

Use text-embedding-3-small for embedding tasks where cost and speed are more important than maximum accuracy. It is an improved version of the ada embedding model.

What should you check before using it?

Compare accuracy vs text-embedding-3-large

text-embedding-3-small trades some accuracy for lower cost and faster performance. Test your specific use case to confirm the accuracy meets your requirements.

Why use it through MixRoute?

Use the compatible endpoint with stable model ID

Use the confirmed compatible endpoint with model ID text-embedding-3-small through MixRoute.

08

Token cost estimator

Live estimate from this page's pricing, not an actual bill

This model has no cache-read price; caching is not counted

09

FAQ

text-embedding-3-small is OpenAI’s improved, more performant version of the ada embedding model. It provides efficient text embeddings for measuring relatedness between pieces of text.

One endpoint, a testable decision

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.