Enum rust_ai::openai::types::model::Model

pub enum Model {
    GPT_4,
    GPT_4_0314,
    GPT_4_32K,
    GPT_4_32K_0314,
    GPT_3_5_TURBO,
    GPT_3_5_TURBO_0301,
    TEXT_DAVINCI_003,
    TEXT_DAVINCI_002,
    TEXT_DAVINCI_EDIT_001,
    CODE_DAVINCI_EDIT_001,
    WHISPER_1,
    TEXT_EMBEDDING_ADA_002,
    TEXT_EMBEDDING_ADA_002_v2,
    TEXT_SEARCH_ADA_DOC_001,
    CODE_DAVINCI_002,
    CODE_CUSHMAN_001,
    TEXT_MODERATION_LATEST,
    TEXT_MODERATION_004,
    TEXT_MODERATION_003,
    TEXT_MODERATION_002,
    TEXT_MODERATION_001,
    TEXT_MODERATION_STABLE,
    TEXT_CURIE_001,
    TEXT_BABBAGE_001,
    TEXT_ADA_001,
    DAVINCI,
    CURIE,
    BABBAGE,
    ADA,
    UNKNOWN,
}

An enum of OpenAI models

Note: GPT-4 are not publicly availble yet (Mar 22, 2023).

Variants

GPT_4

More capable than any GPT-3.5 model, able to do more complex tasks, and optimized for chat. Will be updated with our latest model iteration.

MAX TOKENS	TRAINING DATA	SERIES
8192 tokens	Up to Sep 2021	GPT-4

GPT_4_0314

Snapshot of gpt-4 from March 14th 2023. Unlike gpt-4, this model will not receive updates, and will only be supported for a three month period ending on June 14th 2023.

MAX TOKENS	TRAINING DATA	SERIES
8192 tokens	Up to Sep 2021	GPT-4

GPT_4_32K

Same capabilities as the base gpt-4 mode but with 4x the context length. Will be updated with our latest model iteration.

MAX TOKENS	TRAINING DATA	SERIES
32768 tokens	Up to Sep 2021	GPT-4

GPT_4_32K_0314

Snapshot of gpt-4-32 from March 14th 2023. Unlike gpt-4-32k, this model will not receive updates, and will only be supported for a three month period ending on June 14th 2023.

MAX TOKENS	TRAINING DATA	SERIES
32768 tokens	Up to Sep 2021	GPT-4

GPT_3_5_TURBO

Most capable GPT-3.5 model and optimized for chat at 1/10th the cost of text-davinci-003. Will be updated with our latest model iteration.

MAX TOKENS	TRAINING DATA	SERIES
4096 tokens	Up to Sep 2021	GPT-3.5

GPT_3_5_TURBO_0301

Snapshot of gpt-3.5-turbo from March 1st 2023. Unlike gpt-3.5-turbo, this model will not receive updates, and will only be supported for a three month period ending on June 1st 2023.

MAX TOKENS	TRAINING DATA	SERIES
4096 tokens	Up to Sep 2021	GPT-3.5

TEXT_DAVINCI_003

Can do any language task with better quality, longer output, and consistent instruction-following than the curie, babbage, or ada models. Also supports inserting completions within text.

MAX TOKENS	TRAINING DATA	SERIES
4097 tokens	Up to Sep 2021	GPT-3.5

TEXT_DAVINCI_002

Similar capabilities to text-davinci-003 but trained with supervised fine-tuning instead of reinforcement learning

MAX TOKENS	TRAINING DATA	SERIES
4097 tokens	Up to Sep 2021	GPT-3.5

TEXT_DAVINCI_EDIT_001

CODE_DAVINCI_EDIT_001

Optimized for code-completion tasks

MAX TOKENS	TRAINING DATA	SERIES
8001 tokens	Up to Sep 2021	GPT-3.5

WHISPER_1

TEXT_EMBEDDING_ADA_002

TEXT_EMBEDDING_ADA_002_v2

TEXT_SEARCH_ADA_DOC_001

CODE_DAVINCI_002

Most capable Codex model. Particularly good at translating natural language to code. In addition to completing code, also supports inserting completions within code.

MAX TOKENS	TRAINING DATA	SERIES
8001 tokens	Up to Jun 2021	Codex

CODE_CUSHMAN_001

Almost as capable as Davinci Codex, but slightly faster. This speed advantage may make it preferable for real-time applications.

MAX TOKENS	TRAINING DATA	SERIES
2048 tokens	-	Codex

TEXT_MODERATION_LATEST

Most capable moderation model. Accuracy will be slighlty higher than the stable model

Series: Moderation

TEXT_MODERATION_004

TEXT_MODERATION_003

TEXT_MODERATION_002

TEXT_MODERATION_001

TEXT_MODERATION_STABLE

Almost as capable as the latest model, but slightly older.

Series: Moderation

TEXT_CURIE_001

Very capable, faster and lower cost than Davinci.

MAX TOKENS	TRAINING DATA	SERIES
2049 tokens	Up to Oct 2019	GPT-3

TEXT_BABBAGE_001

Capable of straightforward tasks, very fast, and lower cost.

MAX TOKENS	TRAINING DATA	SERIES
2049 tokens	Up to Oct 2019	GPT-3

TEXT_ADA_001

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

MAX TOKENS	TRAINING DATA	SERIES
2049 tokens	Up to Oct 2019	GPT-3

DAVINCI

Most capable GPT-3 model. Can do any task the other models can do, often with higher quality.

MAX TOKENS	TRAINING DATA	SERIES
2049 tokens	Up to Oct 2019	GPT-3

CURIE

Very capable, but faster and lower cost than Davinci.

MAX TOKENS	TRAINING DATA	SERIES
2049 tokens	Up to Oct 2019	GPT-3

BABBAGE

Capable of straightforward tasks, very fast, and lower cost.

MAX TOKENS	TRAINING DATA	SERIES
2049 tokens	Up to Oct 2019	GPT-3

ADA

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

MAX TOKENS	TRAINING DATA	SERIES
2049 tokens	Up to Oct 2019	GPT-3

UNKNOWN

Trait Implementations

impl Clone for Model

fn clone(&self) -> Model

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Model

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for Model

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Into<&'static str> for Model

fn into(self) -> &'static str

Converts this type into the (usually inferred) input type.

impl PartialEq<Model> for Model

fn eq(&self, other: &Model) -> bool

This method tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

This method tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for Model

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Eq for Model

impl StructuralEq for Model

impl StructuralPartialEq for Model