Skip to main content
The Models API allows you to list available models and retrieve detailed information about specific models.

​
List models

Lists the currently available models and provides basic information about each one such as the owner and availability. 
client.models.list

​
Response

Returns a paginated list of Model objects.
​
object
String
The object type, always list.
​
data
Array
List of model objects.

​
Examples

​
List all models

require "openai"

client = OpenAI::Client.new

models = client.models.list

models.data.each do |model|
  puts "#{model.id} (owned by: #{model.owned_by})"
end

​
Filter models

require "openai"

client = OpenAI::Client.new

models = client.models.list

# Find GPT-4 models
gpt4_models = models.data.select { |m| m.id.include?("gpt-4") }

gpt4_models.each do |model|
  puts model.id
end

​
Retrieve a model

Retrieves a model instance, providing basic information about the model such as the owner and permissioning. 
client.models.retrieve(model)
​
model
String
required
The ID of the model to use for this request (e.g., gpt-4, gpt-3.5-turbo).

​
Response

Returns a Model object.
​
id
String
The model identifier.
​
object
String
The object type, always model.
​
created
Integer
Unix timestamp of when the model was created.
​
owned_by
String
The organization that owns the model.

​
Examples

​
Retrieve model details

require "openai"

client = OpenAI::Client.new

model = client.models.retrieve("gpt-4")

puts "Model ID: #{model.id}"
puts "Owned by: #{model.owned_by}"
puts "Created: #{Time.at(model.created)}"

​
Check model availability

require "openai"

client = OpenAI::Client.new

def model_available?(client, model_id)
  client.models.retrieve(model_id)
  true
rescue => e
  puts "Model not available: #{e.message}"
  false
end

if model_available?(client, "gpt-4-turbo")
  puts "GPT-4 Turbo is available!"
end

​
Delete a fine-tuned model

Delete a fine-tuned model. You must have the Owner role in your organization to delete a model. 
client.models.delete(model)
​
model
String
required
The model to delete. Must be a fine-tuned model that you own.

​
Response

Returns a ModelDeleted object.
​
id
String
The ID of the deleted model.
​
object
String
The object type, always model.
​
deleted
Boolean
Whether the model was successfully deleted.

​
Examples

​
Delete a fine-tuned model

require "openai"

client = OpenAI::Client.new

# Delete a fine-tuned model
result = client.models.delete("ft:gpt-3.5-turbo:my-org:custom-model:id")

if result.deleted
  puts "Model #{result.id} deleted successfully"
else
  puts "Failed to delete model"
end

​
Model types

OpenAI offers various types of models for different use cases:

​
Chat models

  • GPT-4 series: Most capable models for complex tasks
    • gpt-4, gpt-4-turbo, gpt-4o, gpt-4o-mini
  • GPT-3.5 series: Fast and cost-effective
    • gpt-3.5-turbo
  • Reasoning models: Advanced reasoning capabilities
    • o3, o4-mini, o1, o1-mini

​
Embedding models

  • text-embedding-3-small: Fast and efficient
  • text-embedding-3-large: Highest quality
  • text-embedding-ada-002: Legacy model

​
Image models

  • DALL-E: Image generation
    • dall-e-2, dall-e-3
  • GPT Image: Advanced image generation and editing
    • gpt-image-1.5, gpt-image-1, gpt-image-1-mini

​
Audio models

  • TTS: Text-to-speech
    • tts-1, tts-1-hd
  • Whisper: Speech-to-text
    • whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe

​
Completions (Legacy)

  • gpt-3.5-turbo-instruct

​
Model capabilities

require "openai"

client = OpenAI::Client.new

# Get all available models
models = client.models.list

# Group by capability
text_models = models.data.select { |m| m.id.include?("gpt") }
embedding_models = models.data.select { |m| m.id.include?("embedding") }
image_models = models.data.select { |m| m.id.include?("dall-e") || m.id.include?("image") }
audio_models = models.data.select { |m| m.id.include?("tts") || m.id.include?("whisper") }

puts "Text models: #{text_models.map(&:id).join(', ')}"
puts "Embedding models: #{embedding_models.map(&:id).join(', ')}"
puts "Image models: #{image_models.map(&:id).join(', ')}"
puts "Audio models: #{audio_models.map(&:id).join(', ')}"

​
Pagination

The list endpoint returns a Page object that can be iterated: 
require "openai"

client = OpenAI::Client.new

# Iterate through all models
page = client.models.list

page.data.each do |model|
  puts model.id
end

# The Page object contains all models
puts "Total models: #{page.data.length}"

​
Best practices

  • Check availability: Before using a model, verify it’s available in your organization
  • Use appropriate models: Choose models based on your use case (speed vs. capability)
  • Monitor usage: Keep track of which models you’re using for billing purposes
  • Fine-tuned models: Only delete fine-tuned models you’re certain you won’t need
  • Stay updated: New models are regularly released; check the list periodically

Build docs developers (and LLMs) love

Get started for freeTalk to us