New embedding models and API updates
📰 OpenAI News
OpenAI releases new embedding models with lower pricing and updates API for better management and usage understanding
Action Steps
- Explore the new embedding models, including text-embedding-3-small and text-embedding-3-large
- Review the updated pricing for GPT-3.5 Turbo and other models
- Understand how to use the new API features to manage API keys and track usage
- Test the new models and API updates in your applications to optimize performance and cost
Who Needs to Know This
Developers and data scientists on a team can benefit from the new embedding models and API updates to improve their applications and manage API usage more efficiently
Key Insight
💡 The new embedding models provide stronger performance and reduced pricing, making it more efficient for developers to build and manage applications
Share This
🚀 New embedding models and API updates from OpenAI! 💡 Lower pricing and improved performance for developers and data scientists #OpenAI #Embeddings #API
Key Takeaways
OpenAI releases new embedding models with lower pricing and updates API for better management and usage understanding
Full Article
# New embedding models and API updates | OpenAI
[Skip to main content](https://openai.com/index/new-embedding-models-and-api-updates#main)
[](https://openai.com/)
* [Research](https://openai.com/research/index/)
* Products
* [Business](https://openai.com/business/)
* [Developers](https://openai.com/api/)
* [Company](https://openai.com/about/)
* [Foundation(opens in a new window)](https://openaifoundation.org/)
Log in[Try ChatGPT(opens in a new window)](https://chatgpt.com/)
* Research
* Products
* Business
* Developers
* Company
* [Foundation(opens in a new window)](https://openaifoundation.org/)
[Try ChatGPT(opens in a new window)](https://chatgpt.com/)Login
OpenAI
Table of contents
* [New embedding models with lower pricing](https://openai.com/index/new-embedding-models-and-api-updates#new-embedding-models-with-lower-pricing)
* [Other new models and lower pricing](https://openai.com/index/new-embedding-models-and-api-updates#other-new-models-and-lower-pricing)
* [New ways to understand API usage and manage API keys](https://openai.com/index/new-embedding-models-and-api-updates#new-ways-to-understand-api-usage-and-manage-api-keys)
January 25, 2024
[Product](https://openai.com/news/product-releases/)
# New embedding models and API updates
[Read documentation(opens in a new window)](https://platform.openai.com/docs/guides/embeddings/)
Loading…
Share
We are releasing new models, reducing prices for GPT‑3.5 Turbo, and introducing new ways for developers to manage API keys and understand API usage. The new models include:
* Two new embedding models
* An updated GPT‑4 Turbo preview model
* An updated GPT‑3.5 Turbo model
* An updated text moderation model
By default, data sent to the OpenAI API will not be used to train or improve OpenAI models.
## New embedding models with lower pricing
We are introducing two new embedding models: a smaller and highly efficient `text-embedding-3-small` model, and a larger and more powerful `text-embedding-3-large` model.
An [embedding](https://openai.com/index/introducing-text-and-code-embeddings/) is a sequence of numbers that represents the concepts within content such as natural language or code. Embeddings make it easy for machine learning models and other algorithms to understand the relationships between content and to perform tasks like clustering or retrieval. They power applications like knowledge retrieval in both ChatGPT and the Assistants API, and many retrieval augmented generation (RAG) developer tools.
Loading...
### A new small text embedding model
`text-embedding-3-small` is our new highly efficient embedding model and provides a significant upgrade over its predecessor, the `text-embedding-ada-002` model released in [December 2022](https://openai.com/index/new-and-improved-embedding-model/).
**Stronger performance.** Comparing `text-embedding-ada-002` to `text-embedding-3-small`, the average score on a commonly used benchmark for multi-language retrieval ([MIRACL(opens in a new window)](https://github.com/project-miracl/miracl)) has increased from 31.4% to 44.0%, while the average score on a commonly used benchmark for English tasks ([MTEB(opens in a new window)](https://github.com/embeddings-benchmark/mteb)) has increased from 61.0% to 62.3%.
**Reduced price.**`text-embedding-3-small` is also substantially more efficient than our previous generation `text-embedding-ada-002` model. Pricing for `text-embedding-3-small` has therefore been reduced by 5X compared to `text-embedding-ada-002`, from a price per 1k tokens of $0.0001 to $0.00002.
We are not deprecating `text-embedding-ada-002`, so while we recommend the newer model, customers are welcome to continue using the previous generation model.
A
[Skip to main content](https://openai.com/index/new-embedding-models-and-api-updates#main)
[](https://openai.com/)
* [Research](https://openai.com/research/index/)
* Products
* [Business](https://openai.com/business/)
* [Developers](https://openai.com/api/)
* [Company](https://openai.com/about/)
* [Foundation(opens in a new window)](https://openaifoundation.org/)
Log in[Try ChatGPT(opens in a new window)](https://chatgpt.com/)
* Research
* Products
* Business
* Developers
* Company
* [Foundation(opens in a new window)](https://openaifoundation.org/)
[Try ChatGPT(opens in a new window)](https://chatgpt.com/)Login
OpenAI
Table of contents
* [New embedding models with lower pricing](https://openai.com/index/new-embedding-models-and-api-updates#new-embedding-models-with-lower-pricing)
* [Other new models and lower pricing](https://openai.com/index/new-embedding-models-and-api-updates#other-new-models-and-lower-pricing)
* [New ways to understand API usage and manage API keys](https://openai.com/index/new-embedding-models-and-api-updates#new-ways-to-understand-api-usage-and-manage-api-keys)
January 25, 2024
[Product](https://openai.com/news/product-releases/)
# New embedding models and API updates
[Read documentation(opens in a new window)](https://platform.openai.com/docs/guides/embeddings/)
Loading…
Share
We are releasing new models, reducing prices for GPT‑3.5 Turbo, and introducing new ways for developers to manage API keys and understand API usage. The new models include:
* Two new embedding models
* An updated GPT‑4 Turbo preview model
* An updated GPT‑3.5 Turbo model
* An updated text moderation model
By default, data sent to the OpenAI API will not be used to train or improve OpenAI models.
## New embedding models with lower pricing
We are introducing two new embedding models: a smaller and highly efficient `text-embedding-3-small` model, and a larger and more powerful `text-embedding-3-large` model.
An [embedding](https://openai.com/index/introducing-text-and-code-embeddings/) is a sequence of numbers that represents the concepts within content such as natural language or code. Embeddings make it easy for machine learning models and other algorithms to understand the relationships between content and to perform tasks like clustering or retrieval. They power applications like knowledge retrieval in both ChatGPT and the Assistants API, and many retrieval augmented generation (RAG) developer tools.
Loading...
### A new small text embedding model
`text-embedding-3-small` is our new highly efficient embedding model and provides a significant upgrade over its predecessor, the `text-embedding-ada-002` model released in [December 2022](https://openai.com/index/new-and-improved-embedding-model/).
**Stronger performance.** Comparing `text-embedding-ada-002` to `text-embedding-3-small`, the average score on a commonly used benchmark for multi-language retrieval ([MIRACL(opens in a new window)](https://github.com/project-miracl/miracl)) has increased from 31.4% to 44.0%, while the average score on a commonly used benchmark for English tasks ([MTEB(opens in a new window)](https://github.com/embeddings-benchmark/mteb)) has increased from 61.0% to 62.3%.
**Reduced price.**`text-embedding-3-small` is also substantially more efficient than our previous generation `text-embedding-ada-002` model. Pricing for `text-embedding-3-small` has therefore been reduced by 5X compared to `text-embedding-ada-002`, from a price per 1k tokens of $0.0001 to $0.00002.
We are not deprecating `text-embedding-ada-002`, so while we recommend the newer model, customers are welcome to continue using the previous generation model.
A
DeepCamp AI