Enum OpenAIModel 

pub enum OpenAIModel {
    Gpt55Pro,
    Gpt55,
    Gpt54Pro,
    Gpt54,
    Gpt54Mini,
    Gpt54Nano,
    Gpt53ChatLatest,
    Gpt53Codex,
    Gpt52Pro,
    Gpt52,
    Gpt52ChatLatest,
    Gpt52Codex,
    Gpt51,
    Gpt5ChatLatest,
    Gpt5Pro,
    Gpt5,
    Gpt5Nano,
    Gpt5Mini,
    Gpt41,
    Gpt41Mini,
    Gpt41Nano,
    Gpt4O,
    Gpt4OMini,
    Gpt4Turbo,
    Gpt4,
    Gpt35Turbo,
    Custom(String),
}

OpenAI models available for completion

For the latest available models and their identifiers, check the OpenAI Models Documentation.

Using Custom Models

You can specify any model name as a string using Custom variant or FromStr:

use rstructor::OpenAIModel;
use std::str::FromStr;

// Using Custom variant
let model = OpenAIModel::Custom("gpt-4-custom".to_string());

// Using FromStr (useful for config files)
let model = OpenAIModel::from_str("gpt-4-custom").unwrap();

// Or use the convenience method
let model = OpenAIModel::from_string("gpt-4-custom");

Variants

Gpt55Pro

GPT-5.5 Pro (most capable GPT-5.5 model)

Gpt55

GPT-5.5 (latest frontier model for complex professional work)

Gpt54Pro

GPT-5.4 Pro (most capable GPT-5.4-class model)

Gpt54

GPT-5.4 (more affordable frontier model for complex professional work)

Gpt54Mini

GPT-5.4 Mini (lower-latency, lower-cost GPT-5.4-class model)

Gpt54Nano

GPT-5.4 Nano (cheapest GPT-5.4-class model for high-volume tasks)

Gpt53ChatLatest

GPT-5.3 Chat Latest (ChatGPT GPT-5.3 model)

Gpt53Codex

GPT-5.3 Codex (coding-focused GPT-5.3 model)

Gpt52Pro

GPT-5.2 Pro (previous GPT-5.2 pro model)

Gpt52

GPT-5.2 (previous GPT-5.2 model)

Gpt52ChatLatest

GPT-5.2 Chat Latest (ChatGPT GPT-5.2 model)

Gpt52Codex

GPT-5.2 Codex (coding-focused GPT-5.2 model)

Gpt51

GPT-5.1 (GPT-5.1 model)

Gpt5ChatLatest

GPT-5 Chat Latest (ChatGPT GPT-5 model)

Gpt5Pro

GPT-5 Pro (most capable GPT-5 model)

Gpt5

GPT-5 (standard GPT-5 model)

Gpt5Nano

GPT-5 Nano (smallest GPT-5 model)

Gpt5Mini

GPT-5 Mini (smaller, faster GPT-5 model)

Gpt41

GPT-4.1 (GPT-4.1 model)

Gpt41Mini

GPT-4.1 Mini (smaller GPT-4.1)

Gpt41Nano

GPT-4.1 Nano (smallest GPT-4.1)

Gpt4O

GPT-4o (previous GPT-4o model, optimized for chat)

Gpt4OMini

GPT-4o Mini (smaller, faster, more cost-effective version)

Gpt4Turbo

GPT-4 Turbo (high-intelligence model)

Gpt4

GPT-4 (standard GPT-4 model)

Gpt35Turbo

GPT-3.5 Turbo (efficient model for simple tasks)

Custom(String)

Custom model identifier — for new models, local LLMs, or provider-compatible endpoints not covered by a named variant.

Implementations

impl Model

pub fn as_str(&self) -> &str

Return the exact API model identifier for this model.

pub fn from_string(name: impl Into<String>) -> Self

Create a model from a string.

This convenience constructor always succeeds: a known identifier maps to its variant, and anything else becomes Custom.

Trait Implementations

impl Clone for Model

fn clone(&self) -> Model

Returns a duplicate 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 Eq for Model

impl From<&str> for Model

fn from(s: &str) -> Self

Converts to this type from the input type.

impl From<String> for Model

fn from(s: String) -> Self

Converts to this type from the input type.

impl FromStr for Model

type Err = Infallible

The associated error which can be returned from parsing.

fn from_str(s: &str) -> Result<Self, Self::Err>

Parses a string s to return a value of this type.

impl PartialEq for Model

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

Tests for self and other values to be equal, and is used by ==.

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

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

impl StructuralPartialEq for Model