This page is being phased out as part of our documentation reorganization.
Click this card to be redirected to the updated version with the most current information.
If you notice any discrepancies or areas needing improvement in the new documentation, please use the “Report an issue” button at the bottom of the page.
All entities below are based on Pydantic BaseModel and can be found in the entities module.
provider
(string): Provider identifier, e.g., openailabel
(object): Provider display name, i18n, supports en_US (English) and zh_Hans (Chinese)
zh_Hans
(string) [optional]: Chinese label, defaults to en_US if not seten_US
(string): English labeldescription
(object) [optional]: Provider description, i18n
zh_Hans
(string) [optional]: Chinese descriptionen_US
(string): English descriptionicon_small
(string) [optional]: Provider small icon, stored in _assets directory
zh_Hans
(string) [optional]: Chinese iconen_US
(string): English iconicon_large
(string) [optional]: Provider large icon, stored in _assets directory
zh_Hans
(string) [optional]: Chinese iconen_US
(string): English iconbackground
(string) [optional]: Background color value, e.g., #FFFFFF, uses frontend default if emptyhelp
(object) [optional]: Help information
title
(object): Help title, i18n
zh_Hans
(string) [optional]: Chinese titleen_US
(string): English titleurl
(object): Help link, i18n
zh_Hans
(string) [optional]: Chinese linken_US
(string): English linksupported_model_types
(array[ModelType]): Supported model typesconfigurate_methods
(array[ConfigurateMethod]): Configuration methodsprovider_credential_schema
([ProviderCredentialSchema]): Provider credential specificationsmodel_credential_schema
([ModelCredentialSchema]): Model credential specificationsmodel
(string): Model identifier, e.g., gpt-3.5-turbolabel
(object) [optional]: Model display name, i18n
zh_Hans
(string) [optional]: Chinese labelen_US
(string): English labelmodel_type
([ModelType]): Model typefeatures
(array[[ModelFeature]]) [optional]: List of supported featuresmodel_properties
(object): Model properties
mode
([LLMMode]): Mode (available for llm model type)context_size
(int): Context size (available for llm and text-embedding types)max_chunks
(int): Maximum number of chunks (available for text-embedding and moderation types)file_upload_limit
(int): Maximum file upload limit in MB (available for speech2text type)supported_file_extensions
(string): Supported file extensions, e.g., mp3,mp4 (available for speech2text type)default_voice
(string): Default voice, must be one of: alloy,echo,fable,onyx,nova,shimmer (available for tts type)voices
(list): Available voice listmode
(string): Voice model (available for tts type)name
(string): Voice model display name (available for tts type)language
(string): Voice model supported languages (available for tts type)word_limit
(int): Single conversion word limit, defaults to paragraph division (available for tts type)audio_type
(string): Supported audio file extensions, e.g., mp3,wav (available for tts type)max_workers
(int): Maximum concurrent tasks for text-to-audio conversion (available for tts type)max_characters_per_chunk
(int): Maximum characters per chunk (available for moderation type)parameter_rules
(array[ParameterRule]) [optional]: Model call parameter rulespricing
([PriceConfig]) [optional]: Pricing informationdeprecated
(bool): Whether deprecated. If true, model won’t show in list but configured ones can still be used. Default: Falsellm
: Text generation modeltext-embedding
: Text embedding modelrerank
: Rerank modelspeech2text
: Speech to texttts
: Text to speechmoderation
: Moderationpredefined-model
: Predefined models Users only need to configure unified provider credentials to use predefined models under the provider.customizable-model
: Custom models Users need to add credential configurations for each model.fetch-from-remote
: Fetch from remote Similar to predefined-model configuration, only requires unified provider credentials, models are fetched from provider using credential information.agent-thought
: Agent reasoning, generally models over 70B have chain-of-thought capabilityvision
: Visual capability, i.e., image understandingtool-call
: Tool callingmulti-tool-call
: Multiple tool callingstream-tool-call
: Streaming tool callingpredefined-model
: Predefined modelsfetch-from-remote
: Remote modelscompletion
: Text completionchat
: Conversationname
(string): Actual parameter name for model callsuse_template
(string) [optional]: Template usage Five preset variable content configuration templates:
label
(object) [optional]: Labels, i18n
zh_Hans
(string) [optional]: Chinese labelen_US
(string): English labeltype
(string) [optional]: Parameter type
int
: Integerfloat
: Floatstring
: Stringboolean
: Booleanhelp
(string) [optional]: Help information
zh_Hans
(string) [optional]: Chinese help infoen_US
(string): English help inforequired
(bool): Whether required, default Falsedefault
(int/float/string/bool) [optional]: Default valuemin
(int/float) [optional]: Minimum value, only for numeric typesmax
(int/float) [optional]: Maximum value, only for numeric typesprecision
(int) [optional]: Precision, decimal places, only for numeric typesoptions
(array[string]) [optional]: Dropdown options, only for string typeinput
(float): Input price, i.e., Prompt priceoutput
(float): Output price, i.e., Return content priceunit
(float): Price unit, e.g., if priced per 1M tokens, unit token number is 0.000001currency
(string): Currency unitcredential_form_schemas
(array[CredentialFormSchema]): Credential form specificationsmodel
(object): Model identifier, default variable name is ‘model’label
(object): Model form item display name
en_US
(string): Englishzh_Hans
(string) [optional]: Chineseplaceholder
(object): Model prompt content
en_US
(string): Englishzh_Hans
(string) [optional]: Chinesecredential_form_schemas
(array[CredentialFormSchema]): Credential form specificationsvariable
(string): Form item variable namelabel
(object): Form item label
en_US
(string): Englishzh_Hans
(string) [optional]: Chinesetype
([FormType]): Form item typerequired
(bool): Whether requireddefault
(string): Default valueoptions
(array[FormOption]): Form item options for select or radio typesplaceholder
(object): Form item placeholder for text-input type
en_US
(string): Englishzh_Hans
(string) [optional]: Chinesemax_length
(int): Maximum input length for text-input type, 0 means no limitshow_on
(array[FormShowOnObject]): Show when other form items meet conditions, always show if emptytext-input
: Text input componentsecret-input
: Password input componentselect
: Single-select dropdownradio
: Radio componentswitch
: Switch component, only supports true and falselabel
(object): Label
en_US
(string): Englishzh_Hans
(string) [optional]: Chinesevalue
(string): Dropdown option valueshow_on
(array[FormShowOnObject]): Show when other form items meet conditions, always show if emptyvariable
(string): Other form item variable namevalue
(string): Other form item variable valueEdit this page | Report an issue
This page is being phased out as part of our documentation reorganization.
Click this card to be redirected to the updated version with the most current information.
If you notice any discrepancies or areas needing improvement in the new documentation, please use the “Report an issue” button at the bottom of the page.
All entities below are based on Pydantic BaseModel and can be found in the entities module.
provider
(string): Provider identifier, e.g., openailabel
(object): Provider display name, i18n, supports en_US (English) and zh_Hans (Chinese)
zh_Hans
(string) [optional]: Chinese label, defaults to en_US if not seten_US
(string): English labeldescription
(object) [optional]: Provider description, i18n
zh_Hans
(string) [optional]: Chinese descriptionen_US
(string): English descriptionicon_small
(string) [optional]: Provider small icon, stored in _assets directory
zh_Hans
(string) [optional]: Chinese iconen_US
(string): English iconicon_large
(string) [optional]: Provider large icon, stored in _assets directory
zh_Hans
(string) [optional]: Chinese iconen_US
(string): English iconbackground
(string) [optional]: Background color value, e.g., #FFFFFF, uses frontend default if emptyhelp
(object) [optional]: Help information
title
(object): Help title, i18n
zh_Hans
(string) [optional]: Chinese titleen_US
(string): English titleurl
(object): Help link, i18n
zh_Hans
(string) [optional]: Chinese linken_US
(string): English linksupported_model_types
(array[ModelType]): Supported model typesconfigurate_methods
(array[ConfigurateMethod]): Configuration methodsprovider_credential_schema
([ProviderCredentialSchema]): Provider credential specificationsmodel_credential_schema
([ModelCredentialSchema]): Model credential specificationsmodel
(string): Model identifier, e.g., gpt-3.5-turbolabel
(object) [optional]: Model display name, i18n
zh_Hans
(string) [optional]: Chinese labelen_US
(string): English labelmodel_type
([ModelType]): Model typefeatures
(array[[ModelFeature]]) [optional]: List of supported featuresmodel_properties
(object): Model properties
mode
([LLMMode]): Mode (available for llm model type)context_size
(int): Context size (available for llm and text-embedding types)max_chunks
(int): Maximum number of chunks (available for text-embedding and moderation types)file_upload_limit
(int): Maximum file upload limit in MB (available for speech2text type)supported_file_extensions
(string): Supported file extensions, e.g., mp3,mp4 (available for speech2text type)default_voice
(string): Default voice, must be one of: alloy,echo,fable,onyx,nova,shimmer (available for tts type)voices
(list): Available voice listmode
(string): Voice model (available for tts type)name
(string): Voice model display name (available for tts type)language
(string): Voice model supported languages (available for tts type)word_limit
(int): Single conversion word limit, defaults to paragraph division (available for tts type)audio_type
(string): Supported audio file extensions, e.g., mp3,wav (available for tts type)max_workers
(int): Maximum concurrent tasks for text-to-audio conversion (available for tts type)max_characters_per_chunk
(int): Maximum characters per chunk (available for moderation type)parameter_rules
(array[ParameterRule]) [optional]: Model call parameter rulespricing
([PriceConfig]) [optional]: Pricing informationdeprecated
(bool): Whether deprecated. If true, model won’t show in list but configured ones can still be used. Default: Falsellm
: Text generation modeltext-embedding
: Text embedding modelrerank
: Rerank modelspeech2text
: Speech to texttts
: Text to speechmoderation
: Moderationpredefined-model
: Predefined models Users only need to configure unified provider credentials to use predefined models under the provider.customizable-model
: Custom models Users need to add credential configurations for each model.fetch-from-remote
: Fetch from remote Similar to predefined-model configuration, only requires unified provider credentials, models are fetched from provider using credential information.agent-thought
: Agent reasoning, generally models over 70B have chain-of-thought capabilityvision
: Visual capability, i.e., image understandingtool-call
: Tool callingmulti-tool-call
: Multiple tool callingstream-tool-call
: Streaming tool callingpredefined-model
: Predefined modelsfetch-from-remote
: Remote modelscompletion
: Text completionchat
: Conversationname
(string): Actual parameter name for model callsuse_template
(string) [optional]: Template usage Five preset variable content configuration templates:
label
(object) [optional]: Labels, i18n
zh_Hans
(string) [optional]: Chinese labelen_US
(string): English labeltype
(string) [optional]: Parameter type
int
: Integerfloat
: Floatstring
: Stringboolean
: Booleanhelp
(string) [optional]: Help information
zh_Hans
(string) [optional]: Chinese help infoen_US
(string): English help inforequired
(bool): Whether required, default Falsedefault
(int/float/string/bool) [optional]: Default valuemin
(int/float) [optional]: Minimum value, only for numeric typesmax
(int/float) [optional]: Maximum value, only for numeric typesprecision
(int) [optional]: Precision, decimal places, only for numeric typesoptions
(array[string]) [optional]: Dropdown options, only for string typeinput
(float): Input price, i.e., Prompt priceoutput
(float): Output price, i.e., Return content priceunit
(float): Price unit, e.g., if priced per 1M tokens, unit token number is 0.000001currency
(string): Currency unitcredential_form_schemas
(array[CredentialFormSchema]): Credential form specificationsmodel
(object): Model identifier, default variable name is ‘model’label
(object): Model form item display name
en_US
(string): Englishzh_Hans
(string) [optional]: Chineseplaceholder
(object): Model prompt content
en_US
(string): Englishzh_Hans
(string) [optional]: Chinesecredential_form_schemas
(array[CredentialFormSchema]): Credential form specificationsvariable
(string): Form item variable namelabel
(object): Form item label
en_US
(string): Englishzh_Hans
(string) [optional]: Chinesetype
([FormType]): Form item typerequired
(bool): Whether requireddefault
(string): Default valueoptions
(array[FormOption]): Form item options for select or radio typesplaceholder
(object): Form item placeholder for text-input type
en_US
(string): Englishzh_Hans
(string) [optional]: Chinesemax_length
(int): Maximum input length for text-input type, 0 means no limitshow_on
(array[FormShowOnObject]): Show when other form items meet conditions, always show if emptytext-input
: Text input componentsecret-input
: Password input componentselect
: Single-select dropdownradio
: Radio componentswitch
: Switch component, only supports true and falselabel
(object): Label
en_US
(string): Englishzh_Hans
(string) [optional]: Chinesevalue
(string): Dropdown option valueshow_on
(array[FormShowOnObject]): Show when other form items meet conditions, always show if emptyvariable
(string): Other form item variable namevalue
(string): Other form item variable valueEdit this page | Report an issue