# What do all these models do?

there are a lot of models. what do all these models do?

id
babbage
babbage:2020-05-03
babbage-code-search-code
babbage-code-search-text
babbage-search-document
babbage-search-query
babbage-similarity
code-cushman-001
code-davinci-001
code-davinci-002
code-davinci-edit-001
code-search-babbage-code-001
code-search-babbage-text-001
curie
curie:2020-05-03
curie-instruct-beta
curie-search-document
curie-search-query
curie-similarity
curie-similarity-fast
cushman:2020-05-03
davinci
davinci:2020-05-03
davinci-if:3.0.0
davinci-instruct-beta
davinci-instruct-beta:2.0.0
davinci-search-document
davinci-search-query
davinci-similarity
if-curie-v2
if-davinci:3.0.0
if-davinci-v2
text-babbage:001
text-babbage-001
text-curie:001
text-curie-001
text-davinci:001
text-davinci-001
text-davinci-002
text-davinci-edit-001
text-davinci-insert-001
text-davinci-insert-002
text-search-babbage-doc-001
text-search-babbage-query-001
text-search-curie-doc-001
text-search-curie-query-001
text-search-davinci-doc-001
text-search-davinci-query-001
text-similarity-babbage-001
text-similarity-curie-001
text-similarity-davinci-001

3 Likes

Ada, Babbage, Curie, Cushman and Davinci are different models doing the same, but having different size. The model with a higher size tends to give better results, but has a higher price and takes more time to give result (because it requires more computation). Davinci is the model with the biggest size.

The models that have â€ścodeâ€ť in the name are part of â€śCodexâ€ť - they serve the purpose of generating code.

The models that have â€śtextâ€ť in the name serve the purpose of generating plain text (thatâ€™s their primary purpose, but they can also generate code to a small extent).

The models that have â€śsearchâ€ť or â€śsimilarityâ€ť in name are for â€śembeddingsâ€ť - they serve the purpose of finding similar texts (as described in the documentation under â€śembeddingsâ€ť).

The models that have â€śsearch-codeâ€ť in the name are for searching with â€ścodeâ€ť, â€śsearch-textâ€ť is for searching with text. The models that have â€śsearchâ€ť in the name, but not â€ścodeâ€ť are for searching text (â€śdocumentâ€ť is for specyifing the documents among which you search, â€śqueryâ€ť is for the query by which you search). â€śsimilarityâ€ť is for finding similar documents as well, but thereâ€™s some difference between â€śsearchâ€ť and â€śsimilarityâ€ť. From what Iâ€™ve remember itâ€™s mostly about the length of the searched documents.

The models with â€śeditâ€ť are for editing code or text (as opposed to completing it).

The models with â€śinstructâ€ť are the models trained specifically for being able to deal with the input (prompt) in a form or instructions.

The models with â€śinsertâ€ť are for insertions (you pass [insert] in the prompt and it generates text/code in the middle of the prompt, in place where you put â€śinsertâ€ť, instead of generating at the end).

â€ś001â€ť, â€ś002â€ť are different versions. I assume â€ś002â€ť are better than â€ś001â€ť becuase 002 is an improved version of 001.

I donâ€™t know what the models with â€śifâ€ť are.

5 Likes

thank you and excellent! we will try them out as such!

1 Like

Ack. I found this incredibly helpful post after I wrote a page long post asking what the models do. This post should at the top of the Similarity Search / Embeddings doc pages!

3 Likes

what is the role of each model and price per 1000 token?
â€śwhisper-1â€ť : 0.000,
â€śbabbageâ€ť : 0.00,
â€śtext-davinci-003â€ť: 0.00,
â€śdavinciâ€ť: 0.00,
â€śtext-davinci-edit-001â€ť: 0.00,
â€śbabbage-code-search-codeâ€ť: 0.00,
â€śtext-similarity-babbage-001â€ť: 0.00,
â€ścode-davinci-edit-001â€ť: 0.00,
â€śtext-davinci-001â€ť: 0.00,
â€śgpt-4-0613â€ť: 0.00,
â€śbabbage-code-search-textâ€ť: 0.00,
â€śbabbage-similarityâ€ť: 0.00,
â€śgpt-4â€ť: 0.00,
â€śgpt-3.5-turbo-0613â€ť: 0.00,
â€śgpt-3.5-turbo-16k-0613â€ť: 0.00,
â€ścode-search-babbage-text-001â€ť: 0.00,
â€śtext-curie-001â€ť: 0.00,
â€śgpt-3.5-turboâ€ť: 0.00,
â€śgpt-3.5-turbo-16kâ€ť: 0.00,
â€ścode-search-babbage-code-001â€ť: 0.00,
â€ścurie-instruct-betaâ€ť: 0.00,
â€śgpt-3.5-turbo-0301â€ť: 0.00,
â€śdavinci-search-documentâ€ť: 0.00,
â€śdavinci-instruct-betaâ€ť: 0.00,
â€śtext-similarity-curie-001â€ť: 0.00,
â€śtext-search-davinci-query-001â€ť: 0.00,
â€ścurie-search-queryâ€ť: 0.00,
â€śdavinci-search-queryâ€ť: 0.00,
â€śbabbage-search-documentâ€ť: 0.00,
â€śtext-search-curie-query-001â€ť: 0.00,
â€śgpt-4-0314â€ť: 0.00,
â€śtext-search-babbage-doc-001â€ť: 0.00,
â€ścurie-search-documentâ€ť: 0.00,
â€śtext-search-curie-doc-001â€ť: 0.00,
â€śbabbage-search-queryâ€ť: 0.00,
â€śtext-babbage-001â€ť: 0.00,
â€śtext-search-davinci-doc-001â€ť: 0.00,
â€śtext-search-babbage-query-001â€ť: 0.00,
â€ścurie-similarityâ€ť: 0.00,
â€ścurieâ€ť: 0.00,
â€śtext-similarity-davinci-001â€ť: 0.00,
â€śtext-davinci-002â€ť: 0.00,
â€śdavinci-similarityâ€ť: 0.00,

The models can be sorted by their type and price classification by AI:

babbage
babbage-code-search-code
babbage-similarity
babbage-code-search-text
babbage-search-document
babbage-search-query
text-search-babbage-doc-001
text-babbage-001
text-search-babbage-query-001

curie
curie-instruct-beta
curie-search-query
curie-search-document
curie-similarity
text-similarity-curie-001
text-search-curie-query-001
text-search-curie-doc-001

davinci
davinci-search-document
davinci-instruct-beta
davinci-search-query
text-search-davinci-query-001
text-search-davinci-doc-001
text-similarity-davinci-001
text-davinci-003
text-davinci-edit-001
text-davinci-001
text-davinci-002
davinci-similarity

gpt-4-0314
gpt-4-0613
gpt-4
gpt-3.5-turbo-0613
gpt-3.5-turbo-16k-0613
gpt-3.5-turbo-0301

The size and skill of the GPT-3 model goes from ada->babbage->curie->davinci, and so does the price, with a-c being rather simple models with a low number of parameters and dimensions in comparison to d.

The bare name version is an untuned GPT-3 completion engine, the model that a user can fine-tune, while others are pre-tuned for different tasks, some never leaving â€śbetaâ€ť. All of these will be going away in 2024. text-davinci-003 is the only one comparable to ChatGPT.

GPT-3.5 and GPT-4 we know well, they are chat-trained models that use a different API endpoint. The ones with dates are a â€śsnapshotâ€ť (that still seems to get modifications anyway). The name without a date is currently pointed to the latest.

text-embedding-ada-002 is a special case. It uses an embedding endpoint and returns vectors. Other specialized embedding models with â€śsimilarityâ€ť or â€śsearchâ€ť are deprecated in favor of this one.

Whisper is the speech-to-text AI.

Pricing: Pricing

Thank you for your reply. I was curious to know which are embedding model, chat model, InstructGPT, Image Model and so on. For example, davinci-search-document. What it does? embedding or something else. Thanks again for your prompt help.

https://platform.openai.com/docs/guides/embeddings/what-are-embeddings

First-generation embeddings are generated by five different model families tuned for three different tasks: text search, text similarity and code search. The search models come in pairs: one for short queries (-query) and one for long documents (-document).

xxx-instruct-beta are mostly just shortcuts to the new naming text-xxx-001. Models that can follow instructions, but differently than ChatGPT follows your instructions.

Thereâ€™s plenty of documentation if you search, like even the second post in this topic answering your questions.