Class: OpenAI::Models::BetaTool::Beta::BetaTool::ImageGeneration

Inherits:
Internal::Type::BaseModel show all
Defined in:
sig/openai/models/beta/beta_tool.rbs

Defined Under Namespace

Modules: Action, Background, InputFidelity, Model, Moderation, OutputFormat, Quality, Size Classes: InputImageMask

Instance Attribute Summary collapse

Attributes inherited from Internal::Type::BaseModel

#last_response

Instance Method Summary collapse

Methods inherited from Internal::Type::BaseModel

==, #==, #[], #_request_id, #_set_last_response, coerce, #deconstruct_keys, #deep_to_h, dump, #encode_with, fields, hash, #hash, inherited, #inspect, inspect, known_fields, optional, recursively_to_h, required, #to_h, #to_json, #to_s, to_sorbet_type, #to_yaml

Methods included from Internal::Type::Converter

#coerce, coerce, coerce_with_error, dump, #dump, #inspect, inspect, meta_info, new_coerce_state, type_info

Methods included from Internal::Util::SorbetRuntimeSupport

#const_missing, #define_sorbet_constant!, #sorbet_constant_defined?, #to_sorbet_type, to_sorbet_type

Constructor Details

#initialize ⇒ Object

Parameters:

  • action —

    Whether to generate a new image or edit an existing image. Default: auto.

  • background —

    Allows to set transparency for the background of the generated image(s). Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.

    gpt-image-2.5-sunburst and gpt-image-2.5-flare, including their 2026-09-08 snapshots, support opaque and transparent backgrounds. Transparent backgrounds are available for supported GPT Image models. For gpt-image-2 and gpt-image-2-2026-04-21, this support is in preview. When using transparent, set the output format to png or webp.

  • input_fidelity —

    Controls fidelity to the original input image(s). This parameter is supported for GPT image models that support input fidelity. gpt-image-2 and gpt-image-2-2026-04-21 ignore this parameter.

  • input_image_mask —

    Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).

  • model —

    The image generation model to use. One of gpt-image-1, gpt-image-1-mini, gpt-image-1.5, gpt-image-2, gpt-image-2-2026-04-21, gpt-image-2.5-sunburst, gpt-image-2.5-sunburst-2026-09-08, gpt-image-2.5-flare, gpt-image-2.5-flare-2026-09-08, or chatgpt-image-latest. Default: gpt-image-1.

  • moderation —

    Moderation level for the generated image. Default: auto.

  • output_compression —

    Compression level for the output image. Default: 100.

  • output_format —

    The output format of the generated image. One of png, webp, or jpeg. Default: png.

  • partial_images —

    Number of partial images to generate in streaming mode, from 0 (default value) to 3.

  • quality —

    The quality of the generated image. The GPT image models support low, medium, and high. gpt-image-2.5-sunburst and gpt-image-2.5-flare, including their 2026-09-08 snapshots, also support xhigh and max. Default: auto.

  • size —

    The size of the generated images. For gpt-image-2, gpt-image-2-2026-04-21, gpt-image-2.5-sunburst, gpt-image-2.5-sunburst-2026-09-08, gpt-image-2.5-flare, and gpt-image-2.5-flare-2026-09-08, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.

  • type —

    The type of the image generation tool. Always image_generation.



808
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 808

def initialize: (

Instance Attribute Details

#action ⇒ OpenAI::Models::Beta::BetaTool::ImageGeneration::action? (readonly)

Whether to generate a new image or edit an existing image. Default: auto.

Returns:

  • (OpenAI::Models::Beta::BetaTool::ImageGeneration::action, nil) 


615
616
617
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 615

def action
  @action
end

#background ⇒ OpenAI::Models::Beta::BetaTool::ImageGeneration::background? (readonly)

Allows to set transparency for the background of the generated image(s). Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.

gpt-image-2.5-sunburst and gpt-image-2.5-flare, including their 2026-09-08 snapshots, support opaque and transparent backgrounds. Transparent backgrounds are available for supported GPT Image models. For gpt-image-2 and gpt-image-2-2026-04-21, this support is in preview. When using transparent, set the output format to png or webp.

Returns:

  • (OpenAI::Models::Beta::BetaTool::ImageGeneration::background, nil) 


631
632
633
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 631

def background
  @background
end

#input_fidelity ⇒ OpenAI::Models::Beta::BetaTool::ImageGeneration::input_fidelity?

Controls fidelity to the original input image(s). This parameter is supported for GPT image models that support input fidelity. gpt-image-2 and gpt-image-2-2026-04-21 ignore this parameter.

Returns:

  • (OpenAI::Models::Beta::BetaTool::ImageGeneration::input_fidelity, nil) 


649
650
651
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 649

def input_fidelity
  @input_fidelity
end

#input_image_mask ⇒ OpenAI::Beta::BetaTool::ImageGeneration::InputImageMask? (readonly)

Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).

Returns:

  • (OpenAI::Beta::BetaTool::ImageGeneration::InputImageMask, nil) 


653
654
655
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 653

def input_image_mask
  @input_image_mask
end

#model ⇒ OpenAI::Models::Beta::BetaTool::ImageGeneration::model? (readonly)

The image generation model to use. One of gpt-image-1, gpt-image-1-mini, gpt-image-1.5, gpt-image-2, gpt-image-2-2026-04-21, gpt-image-2.5-sunburst, gpt-image-2.5-sunburst-2026-09-08, gpt-image-2.5-flare, gpt-image-2.5-flare-2026-09-08, or chatgpt-image-latest. Default: gpt-image-1.

Returns:

  • (OpenAI::Models::Beta::BetaTool::ImageGeneration::model, nil) 


666
667
668
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 666

def model
  @model
end

#moderation ⇒ OpenAI::Models::Beta::BetaTool::ImageGeneration::moderation? (readonly)

Moderation level for the generated image. Default: auto.

Returns:

  • (OpenAI::Models::Beta::BetaTool::ImageGeneration::moderation, nil) 


678
679
680
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 678

def moderation
  @moderation
end

#output_compression ⇒ Integer? (readonly)

Compression level for the output image. Default: 100.

Returns:

  • (Integer, nil) 


686
687
688
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 686

def output_compression
  @output_compression
end

#output_format ⇒ OpenAI::Models::Beta::BetaTool::ImageGeneration::output_format? (readonly)

The output format of the generated image. One of png, webp, or jpeg. Default: png.

Returns:

  • (OpenAI::Models::Beta::BetaTool::ImageGeneration::output_format, nil) 


693
694
695
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 693

def output_format
  @output_format
end

#partial_images ⇒ Integer? (readonly)

Number of partial images to generate in streaming mode, from 0 (default value) to 3.

Returns:

  • (Integer, nil) 


703
704
705
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 703

def partial_images
  @partial_images
end

#quality ⇒ OpenAI::Models::Beta::BetaTool::ImageGeneration::quality? (readonly)

The quality of the generated image. The GPT image models support low, medium, and high. gpt-image-2.5-sunburst and gpt-image-2.5-flare, including their 2026-09-08 snapshots, also support xhigh and max. Default: auto.

Returns:

  • (OpenAI::Models::Beta::BetaTool::ImageGeneration::quality, nil) 


713
714
715
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 713

def quality
  @quality
end

#size ⇒ OpenAI::Models::Beta::BetaTool::ImageGeneration::size? (readonly)

The size of the generated images. For gpt-image-2, gpt-image-2-2026-04-21, gpt-image-2.5-sunburst, gpt-image-2.5-sunburst-2026-09-08, gpt-image-2.5-flare, and gpt-image-2.5-flare-2026-09-08, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.

Returns:

  • (OpenAI::Models::Beta::BetaTool::ImageGeneration::size, nil) 


735
736
737
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 735

def size
  @size
end

#type ⇒ :image_generation

The type of the image generation tool. Always image_generation.

Returns:

  • (:image_generation) 


612
613
614
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 612

def type
  @type
end

Instance Method Details

#action= ⇒ Object (readonly)

Whether to generate a new image or edit an existing image. Default: auto.



618
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 618

def action=: (

#background= ⇒ Object (readonly)

Allows to set transparency for the background of the generated image(s). Must be one of transparent, opaque, or auto (default value). When auto is used, the model will automatically determine the best background for the image.

gpt-image-2.5-sunburst and gpt-image-2.5-flare, including their 2026-09-08 snapshots, support opaque and transparent backgrounds. Transparent backgrounds are available for supported GPT Image models. For gpt-image-2 and gpt-image-2-2026-04-21, this support is in preview. When using transparent, set the output format to png or webp.



642
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 642

def background=: (

#input_image_mask= ⇒ Object (readonly)

Optional mask for inpainting. Contains image_url (string, optional) and file_id (string, optional).



657
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 657

def input_image_mask=: (

#model= ⇒ Object (readonly)

The image generation model to use. One of gpt-image-1, gpt-image-1-mini, gpt-image-1.5, gpt-image-2, gpt-image-2-2026-04-21, gpt-image-2.5-sunburst, gpt-image-2.5-sunburst-2026-09-08, gpt-image-2.5-flare, gpt-image-2.5-flare-2026-09-08, or chatgpt-image-latest. Default: gpt-image-1.



673
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 673

def model=: (

#moderation= ⇒ Object (readonly)

Moderation level for the generated image. Default: auto.



681
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 681

def moderation=: (

#output_compression= ⇒ Integer (readonly)

Compression level for the output image. Default: 100.

Parameters:

  • (Integer)

Returns:

  • (Integer) 


689
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 689

def output_compression=: (Integer) -> Integer

#output_format= ⇒ Object (readonly)

The output format of the generated image. One of png, webp, or jpeg. Default: png.



697
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 697

def output_format=: (

#partial_images= ⇒ Integer (readonly)

Number of partial images to generate in streaming mode, from 0 (default value) to 3.

Parameters:

  • (Integer)

Returns:

  • (Integer) 


707
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 707

def partial_images=: (Integer) -> Integer

#quality= ⇒ Object (readonly)

The quality of the generated image. The GPT image models support low, medium, and high. gpt-image-2.5-sunburst and gpt-image-2.5-flare, including their 2026-09-08 snapshots, also support xhigh and max. Default: auto.



719
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 719

def quality=: (

#size= ⇒ Object (readonly)

The size of the generated images. For gpt-image-2, gpt-image-2-2026-04-21, gpt-image-2.5-sunburst, gpt-image-2.5-sunburst-2026-09-08, gpt-image-2.5-flare, and gpt-image-2.5-flare-2026-09-08, arbitrary resolutions are supported as WIDTHxHEIGHT strings, for example 1536x864. Width and height must both be divisible by 16 and the requested aspect ratio must be between 1:3 and 3:1. Resolutions above 2560x1440 are experimental, and the maximum supported resolution is 3840x2160. The requested size must also satisfy the model's current pixel and edge limits. The standard sizes 1024x1024, 1536x1024, and 1024x1536 are supported by the GPT image models; auto is supported for models that allow automatic sizing. For dall-e-2, use one of 256x256, 512x512, or 1024x1024. For dall-e-3, use one of 1024x1024, 1792x1024, or 1024x1792.



749
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 749

def size=: (

#to_hash ⇒ {

Returns:

  • ({) 


823
 
# File 'sig/openai/models/beta/beta_tool.rbs', line 823

def to_hash: -> {