EMBEDDINGSTEXT INPUTOUTPUT $0NO CACHE DISCOUNTBATCH ENDPOINT
text-embedding-3-large API Pricing
OpenAI's most capable embedding model for English and non-English retrieval. OpenAI lists it at $0.13/M tokens; embeddings have no separate output-token price in the model page. Pulled directly from developers.openai.com.
Embedding input - per 1M tokens
$0.13/M
Embeddings token cost standard
Output tokens
$0.00/M
No text output billed $0
Cached input - not listed
$0.13/M
No discount shown by OpenAI N/A
Effective - embedding blend
$0.12/M
92/8 formula - output is $0
§ 01 / TERMINAL
Run the numbers.
Live calculator pre-loaded with current text-embedding-3-large embedding rates. Use token counts from your indexing pipeline to estimate one-time and recurring embedding costs.
$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
§ 02 / SCENARIOS
Real-world presets.
RAG INDEX
Help-center index
$0.000/doc
SEARCH
Semantic search catalog
$0.001/item
CLUSTERING
Research notes clustering
$0.000/note
DEDUP
Content dedupe pipeline
$0.000/page
§ 03 / TAPE
Price history.
Input · $0.13/M
Output · $0.00/M
Cached · $0.13/M
JAN 25 Launch at $0.13/M tokensMAY 18 Verified unchanged on OpenAI model docs
§ 04 / TOKENIZER
Paste text. See tokens. See cost.
Estimate · tiktoken-cl100k_base · ≈4 chars/token Auto-counts as you type
This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.
Characters —
Words —
Tokens (estimated) —
Cost as input · uncached —
Cost as output · uncached —
Cost as cached input —
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| text-embedding-3-large Current | $0.13 | $0.00 | $0.12 embedding cost | input-only | Maximum OpenAI embedding quality |
| text-embedding-3-small | $0.02 | $0.00 | $0.02 embedding peer | input-only | text-embedding-3-small |
| GPT-5.4 nano | $0.20 cache $0.02 | $1.25 | $0.15 text model baseline | 400K | Cheap text model, not embeddings |
| GPT-5.4 mini | $0.75 cache $0.07 | $4.50 | $0.54 text model baseline | 400K | Subagents and lightweight generation |
| Gemini 2.5 Flash-Lite | $0.10 cache $0.01 | $0.40 | $0.06 Google budget text | 1M | Budget multimodal model |
Frequently asked.
Practical text-embedding-3-large pricing questions for RAG and semantic-search workloads.
Q · 01 What is the text-embedding-3-large API price? +
OpenAI lists
text-embedding-3-large at $0.13/M tokens. Embedding models bill the text you embed; there is no separate generated-output token charge in the model page.Q · 02 Is there cached-input pricing? +
No cached-input discount is listed for OpenAI embedding models. The calculator therefore keeps cached input at the same price as normal input instead of applying a fake cache discount.
Q · 03 How does this compare with the other OpenAI embedding model? +
text-embedding-3-large is compared against
text-embedding-3-small in the shelf. OpenAI's model docs list text-embedding-3-large at $0.13/M and text-embedding-3-small at $0.02/M.Q · 04 Is Batch API available? +
The OpenAI model page lists the Batch endpoint for embeddings. The model page pricing section shows the same public embedding cost; this page does not assume a lower price unless OpenAI lists it for embeddings.
Q · 05 What release date is used here? +
OpenAI's embedding-model announcement is dated
January 25, 2024 and introduced both text-embedding-3-small and text-embedding-3-large. This page uses 2024-01-25 as the launch point.Q · 06 How accurate is the tokenizer estimate? +
The widget uses a planning estimate of
4.875 characters per token for English text. Exact embedding bills depend on the tokenizer, language, punctuation, whitespace, code, and chunking strategy.