text-embedding-3-small
Embedding model
text-embedding-3-small
$0.02 in per 1M tokens
text-embedding-3-large
Model idtext-embedding-3-large
Price$0.13 in per 1M tokens
Checked29 September 2026
Where it stands
6newer embedding models since its release
- EmbeddingGemma 26 Oct 2026
- Cohere Embed 5 Fast30 Sep 2026
- Cohere Embed 5 Pro30 Sep 2026
- Gemini Embedding 222 Apr 2026
- Cohere Rerank 4 (Pro / Fast)11 Dec 2025
The 5 newest are listed. All embedding models
- Weights
- Closed weights; access is hosted only.
How to call it
2 ways to use text-embedding-3-large, with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| OpenAI API | text-embedding-3-large |
https://api.openai.com/v1/embeddings |
developers.openai.com |
| Azure OpenAI (Microsoft Foundry) | text-embedding-3-large |
learn.microsoft.com |
Pricing
| Input | $0.13 per 1M tokens |
|---|
As published: “per 1M tokens (USD)”.
Source: developers.openai.com, checked 29 September 2026.
Specs
- Input
- Text
- Output
- Text
- Context window
- Not published
- Max output
- Not published
- Open weights
- No
- Licence
- Proprietary
- Released
- 25 January 2024
- Status
- Current
- Type
- Embedding model
What stands out
What its maker marketed at launch, and what people found later, each with its source.
Multilingual embeddings
Most capable OpenAI embedding model for English and non-English tasks.
Shortenable (Matryoshka-style) vectors
Default 3072 dimensions; the `dimensions` API parameter truncates embeddings while keeping semantic quality. Max input 8192 tokens.
Notes
Output is an embedding vector. Still OpenAI’s newest embedding model as of 2026-09.
curl https://api.openai.com/v1/embeddings \
-H "Authorization: Bearer $OPENAI_API_KEY" -H "Content-Type: application/json" \
-d '{"model":"text-embedding-3-large","input":"hello"}'
Sources: