Curie

Curie is extremely powerful, yet very fast. While Davinci is stronger when it comes
to analyzing complicated text, Curie is quite capable for many nuanced tasks like
sentiment classification and summarization. Curie is also quite good at answering
questions and performing Q&A and as a general service chatbot.

Good at: Language translation, complex classification, text sentiment,

summarization

Babbage
Babbage can perform straightforward tasks like simple classification. It’s also quite
capable when it comes to Semantic Search ranking how well documents match up
with search queries.

Good at: Moderate classification, semantic search classification

Ada
Ada is usually the fastest model and can perform tasks like parsing text, address
correction and certain kinds of classification tasks that don’t require too much
nuance. Ada’s performance can often be improved by providing more context.

Good at: Parsing text, simple classification, address correction, keywords

Note: Any task performed by a faster model like Ada can be performed by a more
powerful model like Curie or Davinci.

Finding the right model

Experimenting with Davinci is a great way to find out what the API is capable of
doing. After you have an idea of what you want to accomplish, you can stay with
Davinci if you’re not concerned about cost and speed or move onto Curie or
another model and try to optimize around its capabilities.
You can use this tool that lets you run different models side-by-side to compare
outputs, settings, and response times and then download the data into a .xls
spreadsheet.

Consider semantic search

For tasks involving classification, where you’re trying to find what label best fits a
selection of text, you can often get great performance out of the different models
with Semantic Search. Semantic Search uses an models to provide scores for
different blocks of text for how closely they relate to a query. By focusing the scope
of the model to evaluating the relationship of the query to the different text blocks,
in many cases faster models can outperform themselves compared to the task
being presented to them as a generative one.

Understanding Curie’s capabilities

While Davinci is more capable when it comes to comprehending text and
generating responses that are more nuanced like summarizing for a child or
emulating human speaking patterns, Curie is highly capable of analyzing text,
answering direct questions, and providing key points.

Key points

As an example, Curie can use the Wikipedia entry for Pluto to list out key points
from the text. View example.

This example illustrates that Curie is highly capable of getting important information
from text and very useful for a variety of applications including:

 Turning technical documents into bullet points

  Extracting important information from email
 Getting key points from customer service communication

Report generation

You can extend key point extraction even further by using Curie (or Davinci) to
analyze text and answer specific questions. In this example, we’ll use Curie to read
an email from a customer and provide answers to a preset list of questions. View
example.

It’s worth calling attention to two things that are going on in this prompt that can
help improve overall prompt design:

1. Use a low temperature when extracting data

We’ve set the temperature low because we’re looking for straight-forward answers
to questions that the customer comment provides. We’re not asking the model to
try to be creative with its responses – especially for yes or no questions.

2. Use one API call to answer multiple questions

We’re able to get one API call to answer four questions (more are possible) by
providing a list of questions and then priming the prompt with the number one to
indicate that the answers should relate to the questions that just preceded it.

By asking four questions we get a 4x improvement on the efficiency of the API call.
If this task was previously being accomplished by Davinci with one API call per
question, using Curie and optimizing the prompt this way provides cost efficiency
plus the speed advantage of Curie over Davinci.

Understanding Babbage’s capabilities

Babbage is good at picking up obvious patterns in text and then using that as a
reference to generate text. Babbage can also perform broad classification tasks
like assigning categories to industries, genres and media content. For creative
applications, Babbage is able to understand enough structure to create simple
plots and titles.

Idea iteration

You can give Babbage a prompt as simple as “Provide 7 tips for better YouTube
videos,” and it will automatically create a list of practical advice. You can do this for
just about any topic that is reasonably well known. This can either provide
standalone content or be used as a starting point for a more in-depth tutorial. View
example.

Sentence completion

Babbage can work as a great brainstorming tool and help someone complete their
thoughts. If you start a paragraph or sentence, Babbage can quickly get the
context and serve as a writing assistant. View example.

Plot generation

If you provide Babbage with a list of plot ideas from a specific genre, it can
continue adding to that list. If you select the good ones and delete the others, you
can keep sending the growing list to the API and improve the results.

Understanding Ada’s capabilities

Ada is extremely fast and capable when it comes to tasks where creativity is more
important than precision. This can be very useful for creative applications and for
generating large datasets.

Random data

Ada can quickly generate large amounts of data like names and addresses to be
used for experimenting, building machine models and testing applications.
Character descriptions

You can use Ada to create character descriptions by sending a handful of

examples to the API. By adjusting the temperature and repetition settings you can
control the randomness of the generated examples.

Codex 
Limited beta

The Codex models are descendants of our GPT-3 models that can understand and
generate code. Their training data contains both natural language and billions of
lines of public code from GitHub. Learn more.

They’re most capable in Python and proficient in over a dozen languages including
JavaScript, Go, Perl, PHP, Ruby, Swift, TypeScript, SQL, and even Shell.

We currently offer two Codex models:

MAX TRAINING
LATEST MODEL DESCRIPTION REQUEST DATA

code-davinci-002 Most capable Codex model. Particularly 8,000 Up to Jun

good at translating natural language to tokens 2021
code. In addition to completing code,
also supports inserting completions
within code.

code-cushman-001 Almost as capable as Davinci Codex, Up to

but slightly faster. This speed advantage 2,048
may make it preferable for real-time tokens
applications.

For more, visit our guide to working with Codex.

The Codex models are free to use during the limited beta, and are subject to
reduced rate limits. As we learn about use, we'll look to offer pricing to enable a
broad set of applications.

During this period, you're welcome to go live with your application as long as it
follows our usage policies. We welcome any feedback on these models while in
early use and look forward to engaging with the community.

Feature-specific models
The main Codex models are meant to be used with the text completion endpoint.
We also offer models that are specifically meant to be used with our endpoints
for creating embeddings and editing code.

Content filter
We recommend using our new moderation endpoint instead of the content
filter model.
The filter aims to detect generated text that could be sensitive or unsafe coming
from the API. It's currently in beta mode and has three ways of classifying text-
as safe, sensitive, or unsafe. The filter will make mistakes and we have currently built it
to err on the side of caution, thus, resulting in higher false positives.

Label Descriptions

 0 - The text is safe.

 1 - This text is sensitive. This means that the text could be talking about a
sensitive topic, something political, religious, or talking about a protected
class such as race or nationality.
 2 - This text is unsafe. This means that the text contains profane language,
prejudiced or hateful language, something that could be NSFW, or text that
portrays certain groups/people in a harmful manner.

How do you use the filter?

You need to use the completions endpoint with the content-filter-alpha model and the
following settings:

1. max_tokens set to 1
2. temperature set to 0.0
3. top_p set to 0
4. logprobs set to 10
5. Wrap your prompt in the following way: