ArthurAI Prompts API
The Prompts API from ArthurAI — 12 operation(s) for prompts.
The Prompts API from ArthurAI — 12 operation(s) for prompts.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/arthurai-prompts-api"
curl "https://apis.io/api/v1/apis?limit=25"
Discovery needs no key. Ratings and market analysis are Pro.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: Arthur GenAI Engine Agent Discovery Prompts API
version: 2.1.688
servers:
- url: https://platform.arthur.ai/api
description: Base URL declared by the provider in apis.yml (roadmap#122).
tags:
- name: Prompts
paths:
/api/v1/tasks/{task_id}/prompts/{prompt_name}/versions/{prompt_version}:
get:
tags:
- Prompts
summary: Get an agentic prompt
description: Get an agentic prompt by name and version
operationId: get_agentic_prompt_api_v1_tasks__task_id__prompts__prompt_name__versions__prompt_version__get
security:
- API Key: []
parameters:
- name: prompt_name
in: path
required: true
schema:
type: string
title: Prompt Name
- name: prompt_version
in: path
required: true
schema:
type: string
title: Prompt Version
description: The version of the prompt to retrieve. Can be 'latest', a version number (e.g. '1', '2', etc.), an ISO datetime string (e.g. '2025-01-01T00:00:00'), or a tag.
description: The version of the prompt to retrieve. Can be 'latest', a version number (e.g. '1', '2', etc.), an ISO datetime string (e.g. '2025-01-01T00:00:00'), or a tag.
- name: task_id
in: path
required: true
schema:
type: string
format: uuid
title: Task Id
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/AgenticPrompt'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
delete:
tags:
- Prompts
summary: Delete an agentic prompt version
description: Deletes a specific version of an agentic prompt
operationId: delete_agentic_prompt_version_api_v1_tasks__task_id__prompts__prompt_name__versions__prompt_version__delete
security:
- API Key: []
parameters:
- name: prompt_name
in: path
required: true
schema:
type: string
title: Prompt Name
- name: prompt_version
in: path
required: true
schema:
type: string
title: Prompt Version
description: The version of the prompt to delete. Can be 'latest', a version number (e.g. '1', '2', etc.), an ISO datetime string (e.g. '2025-01-01T00:00:00'), or a tag.
description: The version of the prompt to delete. Can be 'latest', a version number (e.g. '1', '2', etc.), an ISO datetime string (e.g. '2025-01-01T00:00:00'), or a tag.
- name: task_id
in: path
required: true
schema:
type: string
format: uuid
title: Task Id
responses:
'204':
description: Prompt version deleted.
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/tasks/{task_id}/prompts:
get:
tags:
- Prompts
summary: Get all agentic prompts
description: Get all agentic prompts for a given task with optional filtering.
operationId: get_all_agentic_prompts_api_v1_tasks__task_id__prompts_get
security:
- API Key: []
parameters:
- name: task_id
in: path
required: true
schema:
type: string
format: uuid
title: Task Id
- name: sort_by
in: query
required: false
schema:
$ref: '#/components/schemas/LLMMetadataSortField'
description: Field to sort the metadata list by. 'name' (default) preserves the historical alphabetical ordering. 'latest_version_created_at' orders by the most recent version's creation timestamp so that pagination matches the 'last updated' display.
default: name
description: Field to sort the metadata list by. 'name' (default) preserves the historical alphabetical ordering. 'latest_version_created_at' orders by the most recent version's creation timestamp so that pagination matches the 'last updated' display.
- name: sort
in: query
required: false
schema:
$ref: '#/components/schemas/PaginationSortMethod'
description: Sort the results (asc/desc)
default: desc
description: Sort the results (asc/desc)
- name: page_size
in: query
required: false
schema:
type: integer
description: Page size. Default is 10. Must be greater than 0 and less than 5000.
default: 10
title: Page Size
description: Page size. Default is 10. Must be greater than 0 and less than 5000.
- name: page
in: query
required: false
schema:
type: integer
description: Page number
default: 0
title: Page
description: Page number
- name: llm_asset_names
in: query
required: false
schema:
anyOf:
- type: array
items:
type: string
- type: 'null'
description: LLM asset names to filter on using partial matching. If provided, llm assets matching any of these name patterns will be returned
title: Llm Asset Names
description: LLM asset names to filter on using partial matching. If provided, llm assets matching any of these name patterns will be returned
- name: model_provider
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
description: Filter by model provider (e.g., 'openai', 'anthropic', 'azure').
title: Model Provider
description: Filter by model provider (e.g., 'openai', 'anthropic', 'azure').
- name: model_name
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
description: Filter by model name (e.g., 'gpt-4', 'claude-3-5-sonnet').
title: Model Name
description: Filter by model name (e.g., 'gpt-4', 'claude-3-5-sonnet').
- name: created_after
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
description: Inclusive start date for prompt creation in ISO8601 string format. Use local time (not UTC).
title: Created After
description: Inclusive start date for prompt creation in ISO8601 string format. Use local time (not UTC).
- name: created_before
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
description: Exclusive end date for prompt creation in ISO8601 string format. Use local time (not UTC).
title: Created Before
description: Exclusive end date for prompt creation in ISO8601 string format. Use local time (not UTC).
- name: tags
in: query
required: false
schema:
anyOf:
- type: array
items:
type: string
- type: 'null'
description: List of tags to filter for items that have any matching tag across any version.
title: Tags
description: List of tags to filter for items that have any matching tag across any version.
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/LLMGetAllMetadataListResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/tasks/{task_id}/prompts/{prompt_name}/versions:
get:
tags:
- Prompts
summary: List all versions of an agentic prompt
description: List all versions of an agentic prompt with optional filtering.
operationId: get_all_agentic_prompt_versions_api_v1_tasks__task_id__prompts__prompt_name__versions_get
security:
- API Key: []
parameters:
- name: prompt_name
in: path
required: true
schema:
type: string
title: Prompt Name
- name: task_id
in: path
required: true
schema:
type: string
format: uuid
title: Task Id
- name: sort
in: query
required: false
schema:
$ref: '#/components/schemas/PaginationSortMethod'
description: Sort the results (asc/desc)
default: desc
description: Sort the results (asc/desc)
- name: page_size
in: query
required: false
schema:
type: integer
description: Page size. Default is 10. Must be greater than 0 and less than 5000.
default: 10
title: Page Size
description: Page size. Default is 10. Must be greater than 0 and less than 5000.
- name: page
in: query
required: false
schema:
type: integer
description: Page number
default: 0
title: Page
description: Page number
- name: model_provider
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
description: Filter by model provider (e.g., 'openai', 'anthropic', 'azure').
title: Model Provider
description: Filter by model provider (e.g., 'openai', 'anthropic', 'azure').
- name: model_name
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
description: Filter by model name (e.g., 'gpt-4', 'claude-3-5-sonnet').
title: Model Name
description: Filter by model name (e.g., 'gpt-4', 'claude-3-5-sonnet').
- name: created_after
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
description: Inclusive start date for prompt creation in ISO8601 string format. Use local time (not UTC).
title: Created After
description: Inclusive start date for prompt creation in ISO8601 string format. Use local time (not UTC).
- name: created_before
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
description: Exclusive end date for prompt creation in ISO8601 string format. Use local time (not UTC).
title: Created Before
description: Exclusive end date for prompt creation in ISO8601 string format. Use local time (not UTC).
- name: exclude_deleted
in: query
required: false
schema:
type: boolean
description: Whether to exclude deleted prompt versions from the results. Default is False.
default: false
title: Exclude Deleted
description: Whether to exclude deleted prompt versions from the results. Default is False.
- name: min_version
in: query
required: false
schema:
anyOf:
- type: integer
minimum: 1
- type: 'null'
description: Minimum version number to filter on (inclusive).
title: Min Version
description: Minimum version number to filter on (inclusive).
- name: max_version
in: query
required: false
schema:
anyOf:
- type: integer
minimum: 1
- type: 'null'
description: Maximum version number to filter on (inclusive).
title: Max Version
description: Maximum version number to filter on (inclusive).
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/AgenticPromptVersionListResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/completions:
post:
tags:
- Prompts
summary: Run/Stream an unsaved agentic prompt
description: Runs or streams an unsaved agentic prompt
operationId: run_agentic_prompt_api_v1_completions_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CompletionRequest'
required: true
responses:
'200':
description: An AgenticPromptRunResponse object for non-streaming requests or a StreamingResponse which has two events, a chunk event or a final_response event
content:
application/json:
schema:
$ref: '#/components/schemas/AgenticPromptRunResponse'
text/event-stream:
schema:
type: string
example: "# Chunk event\nevent: chunk\ndata: {\n \"id\": \"string\",\n \"created\": 1760636425,\n \"model\": \"string\",\n \"object\": \"string\",\n \"system_fingerprint\": \"string\",\n \"choices\": [\n {\n \"finish_reason\": null,\n \"index\": 0,\n \"delta\": {\n \"provider_specific_fields\": null,\n \"refusal\": null,\n \"content\": \"string\",\n \"role\": null,\n \"function_call\": null,\n \"tool_calls\": null,\n \"audio\": null\n },\n \"logprobs\": null\n }\n ],\n \"provider_specific_fields\": null\n}\n\n# Final response event\nevent: final_response\ndata: {\n \"content\": \"string\",\n \"tool_calls\": [\n \"string\"\n ],\n \"cost\": \"string\"\n}\n\n"
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- API Key: []
/api/v1/prompt_renders:
post:
tags:
- Prompts
summary: Render an unsaved prompt with variables
description: Render an unsaved prompt by replacing template variables with provided values. Accepts messages directly in the request body instead of loading from database.
operationId: render_unsaved_agentic_prompt_api_v1_prompt_renders_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/UnsavedPromptRenderingRequest'
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/RenderedPromptResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- API Key: []
/api/v1/prompt_variables:
post:
tags:
- Prompts
summary: Gets the list of variables needed from an unsaved prompt's messages
description: Gets the list of variables needed from an unsaved prompt's messages
operationId: get_unsaved_prompt_variables_list_api_v1_prompt_variables_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/UnsavedPromptVariablesRequest'
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/UnsavedPromptVariablesListResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- API Key: []
/api/v1/tasks/{task_id}/prompts/{prompt_name}/versions/{prompt_version}/completions:
post:
tags:
- Prompts
summary: Run/Stream a specific version of an agentic prompt
description: Run or stream a specific version of an existing agentic prompt
operationId: run_saved_agentic_prompt_api_v1_tasks__task_id__prompts__prompt_name__versions__prompt_version__completions_post
security:
- API Key: []
parameters:
- name: prompt_name
in: path
required: true
schema:
type: string
title: Prompt Name
- name: prompt_version
in: path
required: true
schema:
type: string
title: Prompt Version
description: The version of the prompt to run. Can be 'latest', a version number (e.g. '1', '2', etc.), an ISO datetime string (e.g. '2025-01-01T00:00:00'), or a tag.
description: The version of the prompt to run. Can be 'latest', a version number (e.g. '1', '2', etc.), an ISO datetime string (e.g. '2025-01-01T00:00:00'), or a tag.
- name: task_id
in: path
required: true
schema:
type: string
format: uuid
title: Task Id
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/PromptCompletionRequest'
default:
variables: []
strict: false
stream: false
responses:
'200':
description: An AgenticPromptRunResponse object for non-streaming requests or a StreamingResponse which has two events, a chunk event or a final_response event
content:
application/json:
schema:
$ref: '#/components/schemas/AgenticPromptRunResponse'
text/event-stream:
schema:
type: string
example: "# Chunk event\nevent: chunk\ndata: {\n \"id\": \"string\",\n \"created\": 1760636425,\n \"model\": \"string\",\n \"object\": \"string\",\n \"system_fingerprint\": \"string\",\n \"choices\": [\n {\n \"finish_reason\": null,\n \"index\": 0,\n \"delta\": {\n \"provider_specific_fields\": null,\n \"refusal\": null,\n \"content\": \"string\",\n \"role\": null,\n \"function_call\": null,\n \"tool_calls\": null,\n \"audio\": null\n },\n \"logprobs\": null\n }\n ],\n \"provider_specific_fields\": null\n}\n\n# Final response event\nevent: final_response\ndata: {\n \"content\": \"string\",\n \"tool_calls\": [\n \"string\"\n ],\n \"cost\": \"string\"\n}\n\n"
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/tasks/{task_id}/prompts/{prompt_name}/versions/{prompt_version}/renders:
post:
tags:
- Prompts
summary: Render a specific version of an agentic prompt with variables
description: Render a specific version of an existing agentic prompt by replacing template variables with provided values. Returns the complete prompt object with rendered messages.
operationId: render_saved_agentic_prompt_api_v1_tasks__task_id__prompts__prompt_name__versions__prompt_version__renders_post
security:
- API Key: []
parameters:
- name: prompt_name
in: path
required: true
schema:
type: string
title: Prompt Name
- name: prompt_version
in: path
required: true
schema:
type: string
title: Prompt Version
description: The version of the prompt to render. Can be 'latest', a version number (e.g. '1', '2', etc.), an ISO datetime string (e.g. '2025-01-01T00:00:00'), or a tag.
description: The version of the prompt to render. Can be 'latest', a version number (e.g. '1', '2', etc.), an ISO datetime string (e.g. '2025-01-01T00:00:00'), or a tag.
- name: task_id
in: path
required: true
schema:
type: string
format: uuid
title: Task Id
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/SavedPromptRenderingRequest'
default:
completion_request:
variables: []
strict: false
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/AgenticPrompt'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/tasks/{task_id}/prompts/{prompt_name}:
post:
tags:
- Prompts
summary: Save an agentic prompt
description: Save an agentic prompt to the database
operationId: save_agentic_prompt_api_v1_tasks__task_id__prompts__prompt_name__post
security:
- API Key: []
parameters:
- name: prompt_name
in: path
required: true
schema:
type: string
title: Prompt Name
- name: task_id
in: path
required: true
schema:
type: string
format: uuid
title: Task Id
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/CreateAgenticPromptRequest'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/AgenticPrompt'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
delete:
tags:
- Prompts
summary: Delete an agentic prompt
description: Deletes an entire agentic prompt
operationId: delete_agentic_prompt_api_v1_tasks__task_id__prompts__prompt_name__delete
security:
- API Key: []
parameters:
- name: prompt_name
in: path
required: true
schema:
type: string
title: Prompt Name
- name: task_id
in: path
required: true
schema:
type: string
format: uuid
title: Task Id
responses:
'204':
description: Prompt deleted.
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/tasks/{task_id}/prompts/{prompt_name}/versions/tags/{tag}:
get:
tags:
- Prompts
summary: Get an agentic prompt by name and tag
description: Get an agentic prompt by name and tag
operationId: get_agentic_prompt_by_tag_api_v1_tasks__task_id__prompts__prompt_name__versions_tags__tag__get
security:
- API Key: []
parameters:
- name: prompt_name
in: path
required: true
schema:
type: string
title: Prompt Name
- name: tag
in: path
required: true
schema:
type: string
title: Tag
- name: task_id
in: path
required: true
schema:
type: string
format: uuid
title: Task Id
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/AgenticPrompt'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/tasks/{task_id}/prompts/{prompt_name}/versions/{prompt_version}/tags:
put:
tags:
- Prompts
summary: Add a tag to an agentic prompt version
description: Add a tag to an agentic prompt version
operationId: add_tag_to_agentic_prompt_version_api_v1_tasks__task_id__prompts__prompt_name__versions__prompt_version__tags_put
security:
- API Key: []
parameters:
- name: prompt_name
in: path
required: true
schema:
type: string
title: Prompt Name
- name: prompt_version
in: path
required: true
schema:
type: string
title: Prompt Version
description: The version of the prompt to retrieve. Can be 'latest', a version number (e.g. '1', '2', etc.), an ISO datetime string (e.g. '2025-01-01T00:00:00'), or a tag.
description: The version of the prompt to retrieve. Can be 'latest', a version number (e.g. '1', '2', etc.), an ISO datetime string (e.g. '2025-01-01T00:00:00'), or a tag.
- name: task_id
in: path
required: true
schema:
type: string
format: uuid
title: Task Id
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/Body_add_tag_to_agentic_prompt_version_api_v1_tasks__task_id__prompts__prompt_name__versions__prompt_version__tags_put'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/AgenticPrompt'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/tasks/{task_id}/prompts/{prompt_name}/versions/{prompt_version}/tags/{tag}:
delete:
tags:
- Prompts
summary: Remove a tag from an agentic prompt version
description: Remove a tag from an agentic prompt version
operationId: delete_tag_from_agentic_prompt_version_api_v1_tasks__task_id__prompts__prompt_name__versions__prompt_version__tags__tag__delete
security:
- API Key: []
parameters:
- name: prompt_name
in: path
required: true
schema:
type: string
title: Prompt Name
- name: prompt_version
in: path
required: true
schema:
type: string
title: Prompt Version
description: The version of the prompt to retrieve. Can be 'latest', a version number (e.g. '1', '2', etc.), an ISO datetime string (e.g. '2025-01-01T00:00:00'), or a tag.
description: The version of the prompt to retrieve. Can be 'latest', a version number (e.g. '1', '2', etc.), an ISO datetime string (e.g. '2025-01-01T00:00:00'), or a tag.
- name: tag
in: path
required: true
schema:
type: string
title: Tag
- name: task_id
in: path
required: true
schema:
type: string
format: uuid
title: Task Id
responses:
'204':
description: Prompt version deleted.
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
components:
schemas:
OpenAIMessage-Output:
properties:
role:
$ref: '#/components/schemas/MessageRole'
description: Role of the message
name:
anyOf:
- type: string
- type: 'null'
title: Name
description: An optional name for the participant. Provides the model information to differentiate between participants of the same role.
content:
anyOf:
- type: string
- items:
$ref: '#/components/schemas/OpenAIMessageItem'
type: array
- type: 'null'
title: Content
description: Content of the message
tool_calls:
anyOf:
- items:
$ref: '#/components/schemas/ToolCall'
type: array
- type: 'null'
title: Tool Calls
description: Tool calls made by assistant
tool_call_id:
anyOf:
- type: string
- type: 'null'
title: Tool Call Id
description: ID of the tool call this message is responding to
type: object
required:
- role
title: OpenAIMessage
description: 'The message schema class for the prompts playground.
This class adheres to OpenAI''s message schema.'
LLMConfigSettings:
properties:
timeout:
anyOf:
- type: number
- type: 'null'
title: Timeout
description: Request timeout in seconds
temperature:
anyOf:
- type: number
- type: 'null'
title: Temperature
description: Sampling temperature (0.0 to 2.0). Higher values make output more random
top_p:
anyOf:
- type: number
- type: 'null'
title: Top P
description: Top-p sampling parameter (0.0 to 1.0). Alternative to temperature
max_tokens:
anyOf:
- type: integer
- type: 'null'
title: Max Tokens
description: Maximum number of tokens to generate in the response
stop:
anyOf:
- type: string
- type: 'null'
title: Stop
description: Stop sequence(s) where the model should stop generating
presence_penalty:
anyOf:
- type: number
- type: 'null'
title: Presence Penalty
description: Presence penalty (-2.0 to 2.0). Positive values penalize new tokens based on their presence
frequency_penalty:
anyOf:
- type: number
- type: 'null'
title: Frequency Penalty
description: Frequency penalty (-2.0 to 2.0). Positive values penalize tokens based on frequency
seed:
anyOf:
- type: integer
- type: 'null'
title: Seed
description: Random seed for reproducible outputs
logprobs:
anyOf:
- type: boolean
- type: 'null'
title: Logprobs
description: Whether to return log probabilities of output tokens
top_logprobs:
anyOf:
- type: integer
- type: 'null'
title: Top Logprobs
description: Number of most likely tokens to return log probabilities for (1-20)
logit_bias:
anyOf:
- items:
$ref: '#/components/schemas/LogitBiasItem'
type: array
- type: 'null'
title: Logit Bias
description: Modify likelihood of specified tokens appearing in completion
max_completion_tokens:
anyOf:
- type: integer
- type: 'null'
title: Max Completion Tokens
description: Maximum number of completion tokens (alternative to max_tokens)
reasoning_effort:
anyOf:
- $ref: '#/components/schemas/ReasoningEffortEnum'
- type: 'null'
description: Reasoning effort level for models that support it (e.g., OpenAI o1 series)
thinking:
anyOf:
- $ref: '#/components/schemas/AnthropicThinkingParam-Output'
- type: 'null'
description: Anthropic-specific thinking parameter for Claude models
tool_choice:
anyOf:
- $ref: '#/components/schemas/ToolChoiceEnum'
- $ref: '#/components/schemas/ToolChoice'
- type: 'null'
title: Tool Choice
description: Tool choice configuration ('auto', 'none', 'required', or a specific tool selection)
response_format:
anyOf:
- $ref: '#/components/schemas/LLMResponseFormat-Output'
- {}
- type: 'null'
title: Response Format
description: Either a structured json_schema or a Pydantic model to en
# --- truncated at 32 KB (65 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/arthurai/refs/heads/main/openapi/arthurai-prompts-api-openapi.yml