Label Studio Subpackage Prompts.subpackage Prompts/versions API
The subpackage_prompts.subpackage_prompts/versions API from Label Studio — 5 operation(s) for subpackage_prompts.subpackage_prompts/versions.
Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
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.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/label-studio-subpackage-prompts-subpackage-prompts-versions-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
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 Specification
openapi: 3.2.0
info:
title: Reference Subpackage Prompts.subpackage Prompts/versions API
version: 1.0.0
servers:
- url: http://localhost:8000
tags:
- name: subpackage_prompts.subpackage_prompts/versions
paths:
/api/prompts/{id}/get-default-version-name:
get:
operationId: get-default-version-name
summary: ✨ Get default prompt version name
description: 'This endpoint is not available in Label Studio Community Edition. Learn more about Label Studio Enterprise
Get default prompt version name'
tags:
- subpackage_prompts.subpackage_prompts/versions
parameters:
- name: id
in: path
required: true
schema:
type: integer
- name: Authorization
in: header
description: 'The token (or API key) must be passed as a request header. You can find your user token on the User Account page in Label Studio. Example: <br><pre><code class="language-bash">curl https://label-studio-host/api/projects -H "Authorization: Token [your-token]"</code></pre>'
required: true
schema:
type: string
responses:
'200':
description: No response body
content:
application/json:
schema:
$ref: '#/components/schemas/prompts_versions_get_default_version_name_Response_200'
/api/prompts/{prompt_id}/versions:
get:
operationId: list
summary: ✨ List prompt versions
description: 'This endpoint is not available in Label Studio Community Edition. Learn more about Label Studio Enterprise
List all versions of a prompt.'
tags:
- subpackage_prompts.subpackage_prompts/versions
parameters:
- name: prompt_id
in: path
required: true
schema:
type: integer
- name: ordering
in: query
description: Which field to use when ordering the results.
required: false
schema:
type: string
- name: Authorization
in: header
description: 'The token (or API key) must be passed as a request header. You can find your user token on the User Account page in Label Studio. Example: <br><pre><code class="language-bash">curl https://label-studio-host/api/projects -H "Authorization: Token [your-token]"</code></pre>'
required: true
schema:
type: string
responses:
'200':
description: ''
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/ThirdPartyModelVersion'
post:
operationId: create
summary: ✨ Create prompt version
description: 'This endpoint is not available in Label Studio Community Edition. Learn more about Label Studio Enterprise
Create a new version of a prompt.'
tags:
- subpackage_prompts.subpackage_prompts/versions
parameters:
- name: prompt_id
in: path
required: true
schema:
type: integer
- name: Authorization
in: header
description: 'The token (or API key) must be passed as a request header. You can find your user token on the User Account page in Label Studio. Example: <br><pre><code class="language-bash">curl https://label-studio-host/api/projects -H "Authorization: Token [your-token]"</code></pre>'
required: true
schema:
type: string
responses:
'201':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/ThirdPartyModelVersion'
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ThirdPartyModelVersionRequest'
/api/prompts/{prompt_id}/versions/{version_id}:
get:
operationId: get
summary: ✨ Get prompt version
description: 'This endpoint is not available in Label Studio Community Edition. Learn more about Label Studio Enterprise
Retrieve a specific prompt of a model.'
tags:
- subpackage_prompts.subpackage_prompts/versions
parameters:
- name: prompt_id
in: path
required: true
schema:
type: integer
- name: version_id
in: path
required: true
schema:
type: integer
- name: Authorization
in: header
description: 'The token (or API key) must be passed as a request header. You can find your user token on the User Account page in Label Studio. Example: <br><pre><code class="language-bash">curl https://label-studio-host/api/projects -H "Authorization: Token [your-token]"</code></pre>'
required: true
schema:
type: string
responses:
'200':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/ThirdPartyModelVersion'
delete:
operationId: delete
summary: ✨ Delete prompt version
description: 'This endpoint is not available in Label Studio Community Edition. Learn more about Label Studio Enterprise
Delete a prompt version by ID'
tags:
- subpackage_prompts.subpackage_prompts/versions
parameters:
- name: prompt_id
in: path
required: true
schema:
type: integer
- name: version_id
in: path
required: true
schema:
type: integer
- name: Authorization
in: header
description: 'The token (or API key) must be passed as a request header. You can find your user token on the User Account page in Label Studio. Example: <br><pre><code class="language-bash">curl https://label-studio-host/api/projects -H "Authorization: Token [your-token]"</code></pre>'
required: true
schema:
type: string
responses:
'200':
description: Successful response
patch:
operationId: update
summary: ✨ Update prompt version
description: 'This endpoint is not available in Label Studio Community Edition. Learn more about Label Studio Enterprise
Update a specific prompt version by ID.'
tags:
- subpackage_prompts.subpackage_prompts/versions
parameters:
- name: prompt_id
in: path
required: true
schema:
type: integer
- name: version_id
in: path
required: true
schema:
type: integer
- name: Authorization
in: header
description: 'The token (or API key) must be passed as a request header. You can find your user token on the User Account page in Label Studio. Example: <br><pre><code class="language-bash">curl https://label-studio-host/api/projects -H "Authorization: Token [your-token]"</code></pre>'
required: true
schema:
type: string
responses:
'200':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/ThirdPartyModelVersion'
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/PatchedThirdPartyModelVersionRequest'
/api/prompts/{prompt_id}/versions/{version_id}/cost-estimate:
get:
operationId: cost-estimate
summary: ✨ Get cost estimate for running a prompt version on a particular project/subset
description: 'This endpoint is not available in Label Studio Community Edition. Learn more about Label Studio Enterprise
Get an estimate of the cost for making an inference run on the selected Prompt Version and Project/ProjectSubset'
tags:
- subpackage_prompts.subpackage_prompts/versions
parameters:
- name: prompt_id
in: path
required: true
schema:
type: integer
- name: version_id
in: path
required: true
schema:
type: integer
- name: Authorization
in: header
description: 'The token (or API key) must be passed as a request header. You can find your user token on the User Account page in Label Studio. Example: <br><pre><code class="language-bash">curl https://label-studio-host/api/projects -H "Authorization: Token [your-token]"</code></pre>'
required: true
schema:
type: string
responses:
'200':
description: Cost estimate response
content:
application/json:
schema:
$ref: '#/components/schemas/InferenceRunCostEstimate'
/api/prompts/{prompt_id}/versions/{version_id}/refine:
get:
operationId: get-refined-prompt
summary: ✨ Get refined prompt
description: 'This endpoint is not available in Label Studio Community Edition. Learn more about Label Studio Enterprise
Get the refined prompt based on the `refinement_job_id`.'
tags:
- subpackage_prompts.subpackage_prompts/versions
parameters:
- name: prompt_id
in: path
required: true
schema:
type: integer
- name: version_id
in: path
required: true
schema:
type: integer
- name: refinement_job_id
in: query
description: Refinement Job ID acquired from the `POST /api/prompts/{prompt_id}/versions/{version_id}/refine` endpoint
required: false
schema:
type: string
- name: Authorization
in: header
description: 'The token (or API key) must be passed as a request header. You can find your user token on the User Account page in Label Studio. Example: <br><pre><code class="language-bash">curl https://label-studio-host/api/projects -H "Authorization: Token [your-token]"</code></pre>'
required: true
schema:
type: string
responses:
'200':
description: Refined prompt response
content:
application/json:
schema:
$ref: '#/components/schemas/RefinedPromptResponse'
post:
operationId: refine-prompt
summary: ✨ Refine a prompt version
description: 'This endpoint is not available in Label Studio Community Edition. Learn more about Label Studio Enterprise
Refine a prompt version using a teacher model and save the refined prompt as a new version.'
tags:
- subpackage_prompts.subpackage_prompts/versions
parameters:
- name: prompt_id
in: path
required: true
schema:
type: integer
- name: version_id
in: path
required: true
schema:
type: integer
- name: async
in: query
description: Whether to run the refinement asynchronously
required: false
schema:
type: boolean
- name: Authorization
in: header
description: 'The token (or API key) must be passed as a request header. You can find your user token on the User Account page in Label Studio. Example: <br><pre><code class="language-bash">curl https://label-studio-host/api/projects -H "Authorization: Token [your-token]"</code></pre>'
required: true
schema:
type: string
responses:
'201':
description: Refined prompt response
content:
application/json:
schema:
$ref: '#/components/schemas/RefinedPromptResponse'
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RefinePromptRequestRequest'
components:
schemas:
ThirdPartyModelVersionRequest:
type: object
properties:
max_few_shot_examples:
type:
- integer
- 'null'
description: Max number of few-shot examples to include in prompts. 0 = disabled.
model_provider_connection:
type:
- integer
- 'null'
organization:
type:
- integer
- 'null'
parent_model:
type: integer
description: Parent model interface ID
prompt:
type: string
description: Prompt to execute
provider:
$ref: '#/components/schemas/ProviderEnum'
description: 'The model provider to use e.g. OpenAI
* `OpenAI` - OpenAI
* `AzureOpenAI` - AzureOpenAI
* `AzureAIFoundry` - AzureAIFoundry
* `VertexAI` - VertexAI
* `Gemini` - Gemini
* `Anthropic` - Anthropic
* `Custom` - Custom'
provider_model_id:
type: string
description: The model ID to use within the given provider, e.g. gpt-3.5
title:
type: string
description: Model name
required:
- prompt
- provider_model_id
- title
title: ThirdPartyModelVersionRequest
prompts_versions_get_default_version_name_Response_200:
type: object
properties: {}
description: Empty response body
title: prompts_versions_get_default_version_name_Response_200
PatchedThirdPartyModelVersionRequest:
type: object
properties:
max_few_shot_examples:
type:
- integer
- 'null'
description: Max number of few-shot examples to include in prompts. 0 = disabled.
model_provider_connection:
type:
- integer
- 'null'
organization:
type:
- integer
- 'null'
parent_model:
type: integer
description: Parent model interface ID
prompt:
type: string
description: Prompt to execute
provider:
$ref: '#/components/schemas/ProviderEnum'
description: 'The model provider to use e.g. OpenAI
* `OpenAI` - OpenAI
* `AzureOpenAI` - AzureOpenAI
* `AzureAIFoundry` - AzureAIFoundry
* `VertexAI` - VertexAI
* `Gemini` - Gemini
* `Anthropic` - Anthropic
* `Custom` - Custom'
provider_model_id:
type: string
description: The model ID to use within the given provider, e.g. gpt-3.5
title:
type: string
description: Model name
title: PatchedThirdPartyModelVersionRequest
InferenceRunCostEstimate:
type: object
properties:
completion_cost_usd:
type:
- string
- 'null'
description: Cost of the completion (in USD)
error_message:
type:
- string
- 'null'
description: Error message details
error_type:
type:
- string
- 'null'
description: Type of error (e.g. "Timeout", "Rate Limit", etc)
is_error:
type:
- boolean
- 'null'
description: Whether an error occurred or not
prompt_cost_usd:
type:
- string
- 'null'
description: Cost of the prompt (in USD)
total_cost_usd:
type:
- string
- 'null'
description: Total cost of the inference (in USD)
title: InferenceRunCostEstimate
UserSimple:
type: object
properties:
avatar:
type: string
email:
type: string
format: email
first_name:
type: string
id:
type: integer
last_name:
type: string
username:
type: string
required:
- avatar
- id
- username
description: 'A ModelSerializer that takes additional arguments for
"fields", "omit" and "expand" in order to
control which fields are displayed, and whether to replace simple
values with complex, nested serializations'
title: UserSimple
RefinePromptRequestRequest:
type: object
properties:
project_id:
type: integer
description: Project ID to target the refined prompt for
teacher_model_name:
type: string
description: Name of the model to use to refine the prompt
teacher_model_provider_connection_id:
type: integer
description: Model Provider Connection ID to use to refine the prompt
required:
- project_id
- teacher_model_name
- teacher_model_provider_connection_id
title: RefinePromptRequestRequest
ThirdPartyModelVersion:
type: object
properties:
created_at:
type: string
format: date-time
created_by:
$ref: '#/components/schemas/UserSimple'
description: User who created Dataset
id:
type: integer
max_few_shot_examples:
type:
- integer
- 'null'
description: Max number of few-shot examples to include in prompts. 0 = disabled.
model_display_name:
type: string
model_provider_connection:
type:
- integer
- 'null'
organization:
type:
- integer
- 'null'
parent_model:
type: integer
description: Parent model interface ID
prompt:
type: string
description: Prompt to execute
provider:
$ref: '#/components/schemas/ProviderEnum'
description: 'The model provider to use e.g. OpenAI
* `OpenAI` - OpenAI
* `AzureOpenAI` - AzureOpenAI
* `AzureAIFoundry` - AzureAIFoundry
* `VertexAI` - VertexAI
* `Gemini` - Gemini
* `Anthropic` - Anthropic
* `Custom` - Custom'
provider_model_id:
type: string
description: The model ID to use within the given provider, e.g. gpt-3.5
score:
type: string
title:
type: string
description: Model name
updated_at:
type: string
format: date-time
required:
- created_at
- created_by
- id
- model_display_name
- prompt
- provider_model_id
- score
- title
- updated_at
title: ThirdPartyModelVersion
ProviderEnum:
type: string
enum:
- OpenAI
- AzureOpenAI
- AzureAIFoundry
- VertexAI
- Gemini
- Anthropic
- Custom
description: '* `OpenAI` - OpenAI
* `AzureOpenAI` - AzureOpenAI
* `AzureAIFoundry` - AzureAIFoundry
* `VertexAI` - VertexAI
* `Gemini` - Gemini
* `Anthropic` - Anthropic
* `Custom` - Custom'
title: ProviderEnum
RefinedPromptResponse:
type: object
properties:
previous_version:
oneOf:
- $ref: '#/components/schemas/ThirdPartyModelVersion'
- type: 'null'
description: Previous version of the prompt
prompt:
type: string
description: The refined prompt text
reasoning:
type:
- string
- 'null'
description: Reasoning behind the refinement
refinement_job_id:
type:
- string
- 'null'
description: Unique identifier for the refinement job
refinement_status:
type:
- string
- 'null'
description: Status of the refinement job
title:
type:
- string
- 'null'
description: Title of the refined prompt
total_cost:
type:
- string
- 'null'
description: Total cost of the refinement job (in USD)
required:
- previous_version
- prompt
- reasoning
- refinement_job_id
- refinement_status
- title
- total_cost
title: RefinedPromptResponse
securitySchemes:
Token:
type: apiKey
in: header
name: Authorization
description: 'The token (or API key) must be passed as a request header. You can find your user token on the User Account page in Label Studio. Example: <br><pre><code class="language-bash">curl https://label-studio-host/api/projects -H "Authorization: Token [your-token]"</code></pre>'