Cody
en
ENESFRDEJAKOPT-BRPLAR
Log in · Assist
Start free
Agents
Cody Assist logoCody AssistKnowledge and supportCody Convert logoCody ConvertProactive website agentCody Clear logoCody ClearCompliance-gradeCody Live logoCody LiveAvatars and experiences
All agentsPricing
Resources
BlogUse casesPrompt librarySkill libraryModel library
Company
AboutContact
All models
Embeddings & vector searchStable
OpenAI

text-embedding-3-large

OpenAI's highest-capability text embedding model for semantic search, recommendations, clustering, and retrieval pipelines.

Open provider docsSee key factsPricing & comparisons

Plain-English overview

What text-embedding-3-large actually is

text-embedding-3-large converts text into numerical vectors that can be stored in a vector database and compared by semantic similarity. It is a practical fit when an application already uses OpenAI and wants one direct API for retrieval alongside generation.

The default vector has 3,072 dimensions. Applications can request fewer dimensions to lower storage and search costs, but should evaluate retrieval quality on their own documents before choosing a smaller representation.

Good fit for

  • High-quality text search and RAG
  • OpenAI-centered application stacks
  • Teams that want adjustable vector size

Category comparison

The facts that matter for embeddings models

These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.

Embedding price
$0.13 / 1M tokensCurrent provider price per million input tokens or the closest published billing unit.
Input capacity
8,191 input tokensMaximum content accepted in one embedding input, using the provider's documented token basis.
Vector dimensions
3,072 default; shorter vectors via dimensionsSupported output sizes; smaller vectors reduce storage while larger vectors may preserve more information.
Accepted inputs
TextText, code, image, audio, video, PDF, or document-aware input supported by the endpoint.
Retrieval controls
Optional dimensions parameter; chunking handled by the applicationQuery/document modes, task types, truncation, chunking, or other controls that shape vectors for retrieval.
Where it runs
OpenAI hosted Embeddings APIDirect API, cloud marketplace, private deployment, or self-hosted route documented by the provider.

Pricing & comparisons

Estimate your cost

Set your usage. Your estimate updates as you type.

Assumes 600 tokens per page, processed separately. Actual token counts vary. This covers embedding only, not storage, search, or generated answers.

text-embedding-3-large

OpenAI

Estimated total (USD)

$0.0008

For the usage above · USD · API pricing, not a subscription

Input tokens
$0.13 per 1M tokens
How this estimate works

Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.

API and provider access

Where to get text-embedding-3-large

OpenAItext-embedding-3-large model docsOfficial model ID, price, input limit, and API endpoint.OpenAIEmbeddings guideRequest examples, dimension shortening, and retrieval guidance.

Availability

Regions and access stage

Available from OpenAI's Embeddings API to supported API accounts.

Direct API access follows OpenAI's supported-country and territory list; third-party cloud routes have their own regional catalogs and terms.

Check live availability

Data and training

The route matters.

OpenAI says business and API data is not used to train its models by default. Abuse-monitoring retention and eligible zero-data-retention controls depend on the endpoint and organization approval.

This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.

Read the provider policy

Frequently asked questions

text-embedding-3-large FAQ

What is text-embedding-3-large?

OpenAI's highest-capability text embedding model for semantic search, recommendations, clustering, and retrieval pipelines. text-embedding-3-large converts text into numerical vectors that can be stored in a vector database and compared by semantic similarity. It is a practical fit when an application already uses OpenAI and wants one direct API for retrieval alongside generation.

When was text-embedding-3-large released?

text-embedding-3-large was released on January 25, 2024 according to the cited provider materials.

Where can I access text-embedding-3-large?

Available from OpenAI's Embeddings API to supported API accounts. The access routes listed in this guide are OpenAI.

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

$0.13 / 1M tokens. OpenAI's standard hosted API list price. The Batch API rate is lower when asynchronous processing fits the workload.

Where is text-embedding-3-large available?

Available from OpenAI's Embeddings API to supported API accounts. Direct API access follows OpenAI's supported-country and territory list; third-party cloud routes have their own regional catalogs and terms.

Is my text-embedding-3-large API data used for training?

OpenAI says business and API data is not used to train its models by default. Abuse-monitoring retention and eligible zero-data-retention controls depend on the endpoint and organization approval. The policy belongs to the provider route and account terms, so verify it again before production use.

Price comparison

USD per million tokens for the shown API routes at standard context length. Cache and long-context rates may differ. Models without matching reviewed prices are omitted; lower cost does not mean better quality.

Input token costsper 1M tokens · USD
  1. $0.10
    Mistral Embed

    Mistral AI

  2. $0.12
    Voyage 4 Large

    Voyage AI

  3. $0.12
    Voyage Context 4

    Voyage AI

  4. $0.12
    Voyage Code 4

    Voyage AI

  5. $0.13
    text-embedding-3-large

    OpenAI

    This model

  6. $0.20
    Gemini Embedding 2

    Google

Related comparisons

Head-to-head comparisons

View category →

  1. text-embedding-3-large vs Gemini Embedding 2

    Google's multimodal embedding model for placing text, images, video, audio, and PDFs in one searchable vector space.

    Open full comparison

  2. text-embedding-3-large vs Cohere Embed 4

    Cohere's enterprise embedding model for multilingual text, images, and visually rich documents with a 128K context window.

    Open full comparison

  3. text-embedding-3-large vs Voyage 4 Large

    Voyage AI's quality-first general embedding model for text and code retrieval, with adjustable dimensions and a shared family vector space.

    Open full comparison

  4. text-embedding-3-large vs Voyage Context 4

    Voyage AI's document-aware embedding model that automatically creates vectors for chunks while preserving information from the surrounding document.

    Open full comparison

  5. text-embedding-3-large vs Voyage Code 4

    Voyage AI's specialist embedding model for finding relevant code from natural-language questions or other source-code context.

    Open full comparison

  6. text-embedding-3-large vs Mistral Embed

    Mistral's straightforward hosted text embedding model for semantic search, clustering, classification, and RAG.

    Open full comparison