OpenAI text-embedding-3-large

Name: OpenAI text-embedding-3-large
Brand: OpenAI
SKU: text-embedding-3-large
Price: 0.156 USD
Availability: InStock

EmbeddingsAvailable

by OpenAItext-embedding-3-large

OpenAI's highest-quality embedding model. Returns 3072-dim vectors by default and supports reducing dimensions via the dimensions parameter. Outperforms text-embedding-3-small and the older ada-002 on MTEB and multilingual MIRACL retrieval benchmarks, for cases where accuracy matters more than cost.

Try it Get API key Compare

Price: $0.156/1M in
Context: 8,191 tokens
Input → output: Text → Vector
Developer: OpenAI
Updated: September 23, 2026

Playground

Try OpenAI text-embedding-3-large

Input & output

$0.156/1M in

Input

0 / 32,000

Text to embed (single string or array of strings)

Compare with (optional)

Runs the model twice (billed twice).

⌘/Ctrl + Enter

Output

The vector appears here.

This run

The price appears once the input is complete.

New here?

10 free credits ($0.10) when you sign up with Google

Usable 24 hours after sign-up, up to 5 runs per day and at most 2 credits per run. Other sign-in methods start without credits.

About OpenAI text-embedding-3-large

TL;DRAs of September 23, 2026

OpenAI text-embedding-3-large is a model by OpenAI in the Embeddings category. On Railwail, OpenAI text-embedding-3-large costs $0.156 / 1M input tokens. The context window holds 8,191 tokens.

text-embedding-3-large is OpenAI's most capable third-generation embedding model. It produces 3072-dim embeddings by default and, like the small variant, supports the dimensions parameter for Matryoshka-style truncation so you can store shorter vectors when needed. It leads OpenAI's lineup on the MTEB English benchmark and on the multilingual MIRACL retrieval benchmark, making it the pick when embedding quality is the priority over price. Use it for high-recall semantic search, deduplication and reranking-style retrieval. Accepts a single string or a batch per request.

Background

About OpenAI

Founded 2015 · San Francisco, California, USA

OpenAI was founded in December 2015 by Sam Altman, Elon Musk, Greg Brockman, Ilya Sutskever, Wojciech Zaremba and John Schulman, and restructured to capped-profit OpenAI LP in 2019. The embedding model family started with text-embedding-ada-001 in 2021, was unified into text-embedding-ada-002 in December 2022 (still the most-used embedding model on Earth at one point) and replaced in January 2024 by text-embedding-3-small and text-embedding-3-large. The v3 release was OpenAI's first to support Matryoshka-style dimension reduction (sale of arbitrary 256-3072 dim vectors from the same model) and beat ada-002 by 20+ percentage points on the MIRACL multilingual retrieval benchmark while costing roughly the same.

Visit OpenAI

Architecture

Transformer bi-encoder with Matryoshka representation learning

OpenAI text-embedding-3-large is the flagship embedding model in the v3 generation. It produces 3,072-dimensional vectors by default with full Matryoshka representation support, so callers can request any dimension between 256 and 3,072 in the API and OpenAI will truncate-and-renormalise without re-running the model. The model accepts up to 8,191 tokens per input and was trained with a contrastive retrieval objective on a curated multilingual web corpus, including search-query/document pairs and large-scale instruction-tuned pairs. It scores 64.6% on MTEB and 54.9% on MIRACL multilingual retrieval, a step up from 61.0% / 31.4% for ada-002. Pricing is $0.00013 per 1k tokens. Output vectors are L2-normalised. Like all OpenAI models the system is closed-source and hosted only. OpenAI has not published a technical paper for the v3 family beyond a launch blog.

Parameters: Undisclosed
Context: 8,191 tokens

Capabilities

3,072-dim vectors with Matryoshka truncation to any 256-3072 size
8,191-token context window for long-document embedding
Multilingual coverage across 100+ languages
State-of-the-art MIRACL multilingual retrieval (~55%)
L2-normalised vectors with cosine similarity
Drop-in upgrade from ada-002 via the same /embeddings endpoint
Best for: production RAG, multilingual search, retrieval-heavy SaaS

Training & license

Not disclosed. OpenAI describes a 'curated multilingual web corpus' with search-query/document pairs and instruction-tuned pairs.

License: Proprietary commercial API. Generated embeddings may be stored and used commercially under the OpenAI Usage Policy.

Safety testing: Embeddings are not subject to content-filter constraints; OpenAI publishes general bias and fairness statements for the embeddings endpoint.

Known limitations

Closed weights, hosted only
Cannot fine-tune the model
3,072-dim full vectors are storage-heavy without truncation
Worse-than-Cohere v3 on some low-resource languages
8,191-token cap may force chunking for very long documents

Research papers

Pricing

Prices in US dollars. Usage is charged from prepaid credits.

Input	$0.156 / 1M tokens

Billed by the tokens each request actually uses.
1 credit = $0.01

Cost calculator

Price calculator

Input tokens

/ req.

Output tokens

/ req.

Requests

Total

$0.02

2 credits

Per request

$0.0002 · 0.02 credits

Each request is rounded up to 0.01 credits.

API

Call OpenAI text-embedding-3-large with your Railwail API key. Use this model ID in the request:

text-embedding-3-largeAPI documentation Get an API key

curl https://railwail.com/api/v1/embeddings \
  -H "Authorization: Bearer $RAILWAIL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-large",
    "input": "The quick brown fox"
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["RAILWAIL_API_KEY"],
    base_url="https://railwail.com/api/v1",
)

res = client.embeddings.create(
    model="text-embedding-3-large",
    input="The quick brown fox",
)

print(len(res.data[0].embedding))

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.RAILWAIL_API_KEY,
  baseURL: "https://railwail.com/api/v1",
});

const res = await client.embeddings.create({
  model: "text-embedding-3-large",
  input: "The quick brown fox"
});

console.log(res.data[0].embedding.length);

Set your key as RAILWAIL_API_KEYCreate API key

Specifications

Model ID: text-embedding-3-large
Developer: OpenAI
Category: Embeddings
Input: Text
Output: Vector
Context window: 8,191 tokens
Billing: By usage (tokens or GPU time)
Model size: Undisclosed
License: Proprietary commercial API. Generated embeddings may be stored and used commercially under the OpenAI Usage Policy.
Catalog entry updated: September 23, 2026

Input parameters

Inputs and settings from the model's input schema. The example in the API section shows which of them the API accepts.

ParameterTypeDefaultAllowed values

inputrequired
Text to embed (single string or array of strings)
Type: Text
Default: –
Allowed values: up to 32,000 characters
dimensions
Type: Integer
Default: 3072
Allowed values: 256 to 3,072
encoding_format
Type: Choice
Default: float
Allowed values: float or base64

Example prompts

Examples from the Railwail catalog. They were not generated live on this page.

FAQ Matching
How do I reset my password?
Code Search
React useEffect cleanup function memory leak

Use cases

What it is used for

Production RAG for ChatGPT-style assistants
Multilingual enterprise search
Semantic deduplication and clustering at scale
Recommendation systems based on text similarity
Embeddings for downstream classification tasks

Related guides

Embedding Models for Search & Science

All models in Embeddings

Frequently asked questions

What is OpenAI text-embedding-3-large?

OpenAI text-embedding-3-large is a model by OpenAI in the Embeddings category. On Railwail you can call it with an API key through the Railwail API.

How much does OpenAI text-embedding-3-large cost on Railwail?

On Railwail, OpenAI text-embedding-3-large costs $0.156 / 1M input tokens. You are charged for what each request actually uses. Usage is paid from prepaid credits; 1 credit equals $0.01.

What is the context window of OpenAI text-embedding-3-large?

The context window of OpenAI text-embedding-3-large holds 8,191 tokens.

How fast is OpenAI text-embedding-3-large?

There are not enough measured runs of OpenAI text-embedding-3-large on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.

Is OpenAI text-embedding-3-large better than OpenAI text-embedding-3-small?

That depends on the task. OpenAI text-embedding-3-large (OpenAI) and OpenAI text-embedding-3-small (OpenAI) are both models in the Embeddings category. The comparison page shows their prices and specifications side by side.

Compare OpenAI text-embedding-3-large and OpenAI text-embedding-3-small

How do I use OpenAI text-embedding-3-large through the API?

Create a Railwail API key and send your request with the model ID text-embedding-3-large. Code examples for curl, Python and JavaScript are in the API section of this page.

Comparable models

All in this category

OpenAI text-embedding-3-smallOpenAI
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.
$0.024/1M in
85 % cheaper per unit
Compare OpenAI text-embedding-3-large vs. OpenAI text-embedding-3-small

Use OpenAI text-embedding-3-large via the API

One API key for every model on Railwail. Usage is charged from prepaid credits, 1 credit = $0.01.

Get API key Browse all models