Text Embedding 3 Large
$0.143
2024-01-25
- Positioning
- Flagship, as the vendor describes it.Source
- Price
- Level 3 of 4 among embedding models ($ is the cheapest), by input price per 1M tokens: $0.10 to under $0.20.
- Vendor-stated speed
- Not shown: the vendor doesn't compare this model's speed.
Three separate signals, not a quality score.
OpenAI high-dimension embeddings — 3072-d vectors for higher retrieval quality. Text Embedding 3 Large is an OpenAI embedding model on ATP Token, billed per 1M input tokens.
Pricing
Embeddings are billed on input tokens only. 3072-dimension output — higher retrieval quality than 3-small, at a higher rate.
Benchmarks
Scores as published by each vendor, not measured by ATP. Test conditions vary, so they are not directly comparable across vendors.
Same controls on every model: project keys, per-project model access, credit budgets, and a log of every request.Set up your organization
Cost estimator
- Input$14.30
$14.30 USD / month · 1,430 credits / month
Quickstart
from openai import OpenAI
client = OpenAI(
base_url="https://api.atptoken.ai/v1",
api_key="atp-•••"
)
r = client.embeddings.create(
model="text-embedding-3-large",
input="petrichor",
)FAQ
- What does Text Embedding 3 Large do?
- Text Embedding 3 Large is an OpenAI embedding model. Send text, get back vectors for search, clustering, and similarity.
- How is Text Embedding 3 Large priced?
- You pay per 1M input tokens. There's no output charge. You only pay when a request succeeds. $1 = 100 credits. See pricing
- How do I call Text Embedding 3 Large on ATP?
- Create a project API key and point any OpenAI-compatible SDK at https://api.atptoken.ai/v1. Set model to "text-embedding-3-large" (the API id, not the display name). Make sure the model is turned on for your project.
Start with $5. Credits never expire.
Create a project key, turn this model on, and pay only for what you use.