OpenAI: text-embedding-3-large

Text Embedding 3 Large is OpenAI's larger embedding model for multilingual semantic search. It is useful when retrieval quality is a priority, with selectable vector dimensions to balance representation size and storage needs.

Compare models

text-embedding-3-large

AvailableOpenAIEmbeddingSync

Input / Output-30%: $0.13 / $0.00$0.091 / $0.00
Context: 8.2K
Modalities: Embedding

About text-embedding-3-large

text-embedding-3-large is OpenAI's most capable embedding model, converting text into vectors for search, clustering, recommendations, anomaly detection, and classification. OpenAI describes it as strong for both English and non-English tasks, and its vector dimensions can be shortened to balance quality against storage. It is the higher-quality option beside text-embedding-3-small and the older ada-002.

Where it works well

Described by OpenAI as its most capable embedding model for English and non-English text.
Selectable output dimensions let you shrink vectors to fit storage or index limits.
Serves search, clustering, recommendations, anomaly detection, and classification from one model.
Available on both the embeddings and batch endpoints for large indexing jobs.

When to choose another model

Larger vectors cost more to store and search than those from text-embedding-3-small.
It embeds text only; images and audio need a different model.
Vectors from it cannot be compared with vectors from other embedding models in one index.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

EmbeddingTokenLab endpoint

POST/v1/embeddings

curl -X POST "https://api.tokenlab.sh/v1/embeddings" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "encoding_format": "float",
  "model": "text-embedding-3-large",
  "input": "The quick brown fox jumps over the lazy dog."
}'

Parameters

Embedding

Parameter	Values and limits	Default	Notes
`dimensions`	≥ 1	Not provided	Positive output vector length. Maximum depends on the model; no additional upper bound is asserted here.
`encoding_format`	float, base64	Not provided	Not provided
`input`	Inputs: ≥ 1, ≤ 2048	Not provided	Input accepts text or token IDs. Each input is limited to 8192 tokens; a request is limited to 300000 tokens in total.
`user`	Not provided	Not provided	Not provided

text-embedding-3-large supports the Embeddings API and optional output dimensions.

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Embedding

per 1M tokens

Official price: Input $0.13 / Output $0.00
Verified price: Input $0.091 / Output $0.00
Discount: -30%

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Embedding	Input $0.13 / Output $0.00	Input $0.091 / Output $0.00	-30%

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 1, 2026, 6:31 AM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open text-embedding-3-large in Console with a prompt ready to edit or send.

Help me try text-embedding-3-large with embedding at /v1/embeddings. Show the result and cost.

Use cases

Multilingual semantic search
Index documents in several languages and retrieve results by meaning across all of them from a single query.
High-precision RAG
Retrieve passages for a question-answering system where retrieval quality is the bottleneck.
Document clustering
Group similar tickets, articles, or reports into clusters so that recurring themes become visible to analysts.
Shortened vectors
Reduce dimensions to fit a vector database while keeping most of the quality.

Prompt examples

Embed these 5,000 product descriptions for semantic search across English, German, and Japanese queries.

Embed support articles so I can retrieve the three closest to a customer question.

Embed these paragraphs and cluster them into topics.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

What kind of model is text-embedding-3-large?

It is OpenAI's most capable embedding model, producing numeric vectors that measure how related two pieces of text are. It targets English and non-English tasks such as search, clustering, and classification.

Can I reduce the vector size?

Yes. The model supports selectable dimensions, so you can shorten vectors to save storage and search time at some cost in quality. Test your retrieval metrics at the size you plan to use.

How is it different from text-embedding-3-small?

Large is the higher-quality model with bigger vectors, while small is the economical one. Use large when retrieval accuracy is critical and small when volume and cost dominate.

Can I mix its vectors with another model's?

No. Vectors from different models live in different spaces and should not be compared. Re-embed your whole corpus when you change models, and keep query and document vectors from the same model.

Which endpoints can I call?

It works with the embeddings endpoint and the batch endpoint. Chat and audio endpoints are not supported, so use it only for turning text into vectors and pair it with a separate generation model.

How much does text-embedding-3-large cost?

On TokenLab, text-embedding-3-large costs Input $0.091 / Output $0.00 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should text-embedding-3-large use?

Use https://api.tokenlab.sh/v1/embeddings for text-embedding-3-large. The request example below shows the matching code shape.

Which operations does text-embedding-3-large support?

text-embedding-3-large supports Embedding. Select an operation above to see its endpoint and request example.