OpenAI text-embedding-3-small
OpenAI's small, low-cost embedding model. Returns 1536-dim vectors by default and supports shortening output dimensions via the dimensions parameter without retraining. Replaced text-embedding-ada-002 with better retrieval quality at a fraction of the price, and is the default choice for general-purpose semantic search and RAG.
OpenAI text-embedding-3-small is embeddings AI model from OpenAI, priced at €0.020 per 1M input tokens with a 8.2K tokens context window.
About this model
Examples
See what OpenAI text-embedding-3-small can generate
Semantic Search
Input:
"How to deploy a Node.js app to production"
Similar matches:
Deploying Node applications to cloud servers
94%Setting up a Node.js production environment
89%Node.js deployment best practices and CI/CD
85%Document Clustering
Input:
"Machine learning model training techniques"
Similar matches:
Deep learning optimization and hyperparameter tuning
91%Neural network training strategies for beginners
87%Supervised learning algorithms and model evaluation
83%Pricing
API Integration
Use our OpenAI-compatible API to integrate OpenAI text-embedding-3-small into your application.
npm install railwailimport railwail from "railwail";
const rw = railwail("YOUR_API_KEY");
const vectors = await rw.run("text-embedding-3-small", "Hello world", { type: "embed" });
console.log(vectors[0].length); // embedding dimensions
// Or use the embed() method for full control
const res = await rw.embed("text-embedding-3-small", ["Hello", "World"]);
for (const item of res.data) {
console.log(item.embedding.length);
}Deep dive — OpenAI's OpenAI text-embedding-3-small
OpenAI was founded in December 2015 by Sam Altman, Elon Musk, Greg Brockman, Ilya Sutskever, Wojciech Zaremba and John Schulman and restructured to a capped-profit company in 2019. The embedding line started with text-embedding-ada-001 (2021), was unified into ada-002 (December 2022) and replaced in January 2024 by the v3 generation. text-embedding-3-small is the smaller, cheaper sibling of text-embedding-3-large: it beats ada-002 by ~5 points on MTEB at one fifth the price ($0.00002 per 1k tokens). Together with the large variant it was the first OpenAI embedding model to support Matryoshka-style dimension shortening, allowing callers to choose any vector size between 256 and 1,536 without retraining or quality drop.
Visit OpenAI →OpenAI text-embedding-3-small is the entry-level embedding model in the v3 generation. It produces 1,536-dimensional vectors by default and supports the same Matryoshka shortening as the large variant, so callers can request any dimension between 256 and 1,536 in the API and OpenAI will truncate-and-renormalise on the fly. Maximum input length is 8,191 tokens. Training used a contrastive retrieval objective on a curated multilingual web corpus including search-query/document pairs. The model scores around 62.3% MTEB and 44.0% MIRACL multilingual retrieval, a clear step up from 61.0% / 31.4% for ada-002, while being roughly five times cheaper and faster. It is positioned as the default embedding model for cost-sensitive production RAG and large-scale search. Like all OpenAI models the system is closed-source and hosted only.
- Parameters
- Undisclosed (smaller than text-embedding-3-large)
- Context
- 8.2K tokens
- 1,536-dim vectors with Matryoshka truncation to any 256-1,536 size
- 8,191-token context window for long-document embedding
- Multilingual coverage across 100+ languages
- $0.00002 per 1k tokens (~5x cheaper than text-embedding-3-large)
- Drop-in upgrade from ada-002 via the same /embeddings endpoint
- L2-normalised vectors with cosine similarity
- Best for: cost-sensitive RAG, large-scale search, embeddings at high QPS
Not disclosed. OpenAI describes a 'curated multilingual web corpus' with search-query/document pairs.
License: Proprietary commercial API. Generated embeddings may be stored and used commercially under the OpenAI Usage Policy.
Known limitations
- Closed weights, hosted only
- Cannot fine-tune the model
- Lower MTEB / MIRACL scores than text-embedding-3-large
- Multilingual quality below Cohere v3 for some low-resource languages
- 8,191-token cap may force chunking for long documents
Frequently asked questions
Related Models
View all EmbeddingsBGE Large EN v1.5
BAAI (Beijing Academy of AI) open-weight English embedding model with 335M parameters. Returns 1024-dim vectors and was a top MTEB English retrieval model on release. The v1.5 update improved similarity distribution so it works well without a query instruction prefix for symmetric tasks. A widely used open alternative to hosted embeddings.
BGE-M3 (Multilingual)
BAAI multilingual embedding model covering 100+ languages with an 8192-token context. M3 stands for its multi-functionality (dense, sparse and ColBERT-style multi-vector retrieval), multilinguality and multi-granularity over long documents. Returns 1024-dim dense vectors and is a strong open choice for cross-lingual and long-text retrieval.
ESM-2 650M (Protein Embeddings)
Meta AI 650M-parameter protein language model trained on UniRef50 sequences. Feed it an amino-acid sequence and the per-residue hidden states act as learned protein embeddings, used for structure prediction, variant-effect and function tasks. This 33-layer checkpoint is the common balance of quality and cost in the ESM-2 family.
Nomic Embed Text v1.5
Nomic AI open embedding model with a fully reproducible training pipeline (open weights, data and code). Supports an 8192-token context and Matryoshka representation learning, so you can truncate the 768-dim output down to 64 dims with graceful quality loss. Uses task prefixes like search_query and search_document.
Start using OpenAI text-embedding-3-small today
Get started with free credits. No credit card required. Access OpenAI text-embedding-3-small and 100+ other models through a single API.