Enterprise DNAEnterprise DNA
LModels
OpenAI logo

text-embedding-3-large

by OpenAI

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Visit OpenAISubmit your build →
T

Models

text-embedding-3-large

Added 13 July 2026

#openai#temperature

Overview

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Best for

Best for
Text retrieval embeddings

How to use / API access

Call via other with model id `openai/text-embedding-3-large`.

  • other · openai/text-embedding-3-large

OpenRouter id: openai/text-embedding-3-large

Notes

text-embedding-3-large is listed in the EDNA Models directory, sourced from models.dev.

Pros

  • Building semantic search over text chunks
  • text input; embeddings output on the listed OpenRouter route

Cons

  • Using embedding similarity as a factual answer
  • Changing vector dimensions without rebuilding the index
  • Base text-token rates exclude other modalities, tools, caching, retries and any hosting-specific charges. Check actual usage before comparing cost per successful task.
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →

USAGE / OPENROUTER

How much text-embedding-3-large is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
44.4B ▲70.2%
Requests, last 7 days
21.4M
Tool calls, last 7 days
—
012.5B25B19 Sept: 3.5B tokens, 1.9M requests20 Sept: 2.6B tokens, 2.2M requests21 Sept: 4.1B tokens, 3.5M requests22 Sept: 4.7B tokens, 3.2M requests23 Sept: 4B tokens, 2.8M requests24 Sept: 4.1B tokens, 2.8M requests25 Sept: 2.8B tokens, 2.7M requests26 Sept: 2.2B tokens, 2.1M requests27 Sept: 1.7B tokens, 1.9M requests28 Sept: 4.5B tokens, 3.1M requests29 Sept: 5.7B tokens, 3.6M requests30 Sept: 7.2B tokens, 3.6M requests1 Oct: 4.2B tokens, 2.8M requests2 Oct: 5.5B tokens, 2.7M requests3 Oct: 2.9B tokens, 2.6M requests4 Oct: 2.7B tokens, 3M requests5 Oct: 4.1B tokens, 3.4M requests6 Oct: 5.5B tokens, 2.8M requests7 Oct: 4.7B tokens, 2.9M requests8 Oct: 3.2B tokens, 2.6M requests9 Oct: 4.7B tokens, 2.6M requests10 Oct: 1.9B tokens, 2.4M requests11 Oct: 2B tokens, 2M requests12 Oct: 2.9B tokens, 3M requests13 Oct: 5.8B tokens, 3.2M requests14 Oct: 3.8B tokens, 3.3M requests15 Oct: 20.5B tokens, 3.6M requests16 Oct: 4B tokens, 3.2M requests17 Oct: 3.6B tokens, 2.5M requests18 Oct: 3.9B tokens, 2.6M requests19 Sept3 Oct17 Oct18 OctSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with text-embedding-3-large.

Specifications reviewed; no EDNA task evaluation has been run. Sources checked 2026-10-20. Hosting routes and app features can differ.

DeveloperOpenAI
Exact model identifieropenai/text-embedding-3-large
Inputtext
Outputembeddings
Tool calling
Not established
Structured output
Not established
Reasoning controls
Not established
Availability
available
Price basis
token
Licence verification
Check the developer licence; the model name is insufficient

Base text-token rates exclude other modalities, tools, caching, retries and any hosting-specific charges. Check actual usage before comparing cost per successful task.

Consider it for

  • Building semantic search over text chunks
  • Comparing retrieval relevance against a known answer set

Watch for

  • Using embedding similarity as a factual answer
  • Changing vector dimensions without rebuilding the index

PRACTICAL EXERCISE / NOT RUN BY ENTERPRISE DNA

Try the model on a small, checkable task.

Embed query: reset a forgotten password. Compare documents: A account recovery steps, B delivery times, C choosing a strong password. Rank similarities and keep document IDs.

Check the result: All vectors use the same model and dimensions; review whether A is ranked above unrelated B.

Compare another approach

google gemini embedding 2 ↗qwen qwen3 embedding 8b ↗
Inspect the sources and their scope
provider source ↗

Developer documentation for model family or task. OpenRouter route-specific properties remain catalogue claims; EDNA has not executed a task evaluation.

Checked 2026-10-19
catalogue source ↗

openai/text-embedding-3-large: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-10-20
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Understand the capabilitiesRead the model guide ↗

Check the source

Price date: 2026-10-20. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Compare this model with alternatives →