NewFineTunedModel converts a string to FineTunedModel.

Ada is capable of very simple tasks, usually the fastest model in the GPT-3 series, and lowest cost.

Deprecated: OpenAI recommends using text-embedding-ada-002 for nearly all use cases.

Deprecated: OpenAI recommends using text-embedding-ada-002 for nearly all use cases.

AdaEmbeddingV2 is the second-generation embedding model.

Deprecated: OpenAI recommends using text-embedding-ada-002 for nearly all use cases.

Deprecated: OpenAI recommends using text-embedding-ada-002 for nearly all use cases.

Deprecated: OpenAI recommends using text-embedding-ada-002 for nearly all use cases.

Babbage is capable of straightforward tasks, very fast, and lower cost.

Deprecated: OpenAI recommends using text-embedding-ada-002 for nearly all use cases.

Deprecated: OpenAI recommends using text-embedding-ada-002 for nearly all use cases.

Deprecated: OpenAI recommends using text-embedding-ada-002 for nearly all use cases.

Deprecated: OpenAI recommends using text-embedding-ada-002 for nearly all use cases.

Deprecated: OpenAI recommends using text-embedding-ada-002 for nearly all use cases.

CodeCushman001 is almost as capable as Davinci Codex, but slightly faster.

CodeDavinci001 is and older version of the most capable Codex model.

CodeDavinci002 is the most capable Codex model.

CodeDavinciEdit001 ...

Curie is very capable, but faster and lower cost than Davinci.

CurieInstructBeta is very capable, but faster and lower cost than Davinci.

Deprecated: OpenAI recommends using text-embedding-ada-002 for nearly all use cases.

Deprecated: OpenAI recommends using text-embedding-ada-002 for nearly all use cases.

Deprecated: OpenAI recommends using text-embedding-ada-002 for nearly all use cases.

Davinci most capable of the older versions of the GPT-3 models and is intended to be used with the fine-tuning endpoints.

DavinciInstructBeta is the most capable model in the InstructGPT series.

Deprecated: OpenAI recommends using text-embedding-ada-002 for nearly all use cases.

Deprecated: OpenAI recommends using text-embedding-ada-002 for nearly all use cases.

Deprecated: OpenAI recommends using text-embedding-ada-002 for nearly all use cases.

GPT3Dot5Turbo is the most capable GPT-3.5 model and optimized for chat at 1/10th the cost of text-davinci-003.

GPT3Dot5Turbo0125 is the latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls.

GPT3Dot5Turbo0301 is a snapshot of gpt-3.5-turbo from March 1st 2023.

GPT3Dot5Turbo0613 includes the same function calling as GPT-4 as well as more reliable steerability via the system message, two features that allow developers to guide the model's responses more effectively.

GPT3Dot5Turbo1106 is a GPT-3.5 Turbo model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more.

GPT3Dot5Turbo16K offers 4 times the context length of gpt-3.5-turbo at twice the price: $0.003 per 1K input tokens and $0.004 per 1K output tokens.

GPT4 is more capable than any GPT-3.5 model, able to do more complex tasks, and optimized for chat.

GPT4_0314 is a snapshot of gpt-4 from March 14th 2023.

GPT4_0613 includes an updated and improved model with function calling.nolint:revive,stylecheck // This would be unreadable otherwise.

GPT4_32K has the same capabilities as the base gpt-4 mode but with 4x the context length.

GPT4_32K_0314 is a snapshot of gpt-4-32 from March 14th 2023.

GPT4_32K_0613 includes the same improvements as gpt-4-0613, along with an extended context length for better comprehension of larger texts.nolint:revive,stylecheck // This would be unreadable otherwise.

GPT4o (GPT-4o) is the most advanced model.

GPT4o20240503 is a snapshot of gpt-4o from May 13th, 2024.

GPT4Turbo0125Preview (GPT-4 Turbo) is the latest GPT-4 model intended to reduce cases of "laziness" where the model doesn’t complete a task.

GPT4Turbo1106Preview (GPT-4 Turbo) is more capable and has knowledge of world events up to April 2023.

GPT4TurboPreview (GPT-4 Turbo) is the latest GPT-4.

O1Mini is a part of the o1 series of large language models, which are trained with reinforcement learning to perform complex reasoning.

O1Preview is a part of the o1 series of large language models, which are trained with reinforcement learning to perform complex reasoning.

TextAda001 is capable of very simple tasks, usually the fastest model in the GPT-3 series, and lowest cost.

TextBabbage001 is capable of straightforward tasks, very fast, and lower cost.

TextCurie001 is very capable, but faster and lower cost than Davinci.

TextDavinci001 ..

TextDavinci002 is an older version of the most capable GPT-3 model.

TextDavinci003 is the most capable GPT-3 model.

TextDavinciEdit001 ...

TextDavinciInsert001 was a beta model released for insertion.

TextDavinciInsert002 was a beta model released for insertion.

TextModerationLatest ...

TextModerationStable ...

Unknown represents an invalid Embedding model.

UnknownChatCompletion represents an invalid ChatCompletion model.

UnknownCompletion represents an invalid Completion model.

UnknownEdit represents and invalid Edit model.

UnknownModeration represents and invalid Moderation model.

Completion represents all models available for use with the Completions endpoint.

Edit represents all models available for use with the Edits endpoint.

Embedding enumerates the models which can be used to generate Embedding vectors.

FineTunedModel represents the name of a fine-tuned model which was previously generated.

Moderation represents all models available for use with the CreateModeration endpoint.