Vellum AI Execute Prompt Stream API
The Execute Prompt Stream API from Vellum AI — 1 operation(s) for execute prompt stream.
The Execute Prompt Stream API from Vellum AI — 1 operation(s) for execute prompt stream.
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/vellum-execute-prompt-stream-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: Client SDK Execute Prompt Stream API
version: 1.0.0
servers:
- url: https://predict.vellum.ai
- url: https://api.vellum.ai
- url: https://documents.vellum.ai
tags:
- name: Execute Prompt Stream
paths:
/v1/execute-prompt-stream:
post:
operationId: execute-prompt-stream
summary: Execute Prompt Stream
description: Executes a deployed Prompt and streams back the results.
tags:
- Execute Prompt Stream
parameters:
- name: X-API-KEY
in: header
required: true
schema:
type: string
- name: X-API-Version
in: header
required: false
schema:
type: string
responses:
'200':
description: ''
content:
text/event-stream:
schema:
$ref: '#/components/schemas/ExecutePromptEvent'
'400':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/ExecutePromptApiErrorResponse'
'403':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/ExecutePromptApiErrorResponse'
'404':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/ExecutePromptApiErrorResponse'
'500':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/ExecutePromptApiErrorResponse'
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ExecutePromptStreamRequest'
components:
schemas:
DocumentChatMessageContentRequest:
type: object
properties:
type:
$ref: '#/components/schemas/DocumentEnum'
value:
$ref: '#/components/schemas/VellumDocumentRequest'
required:
- type
- value
description: A document value that is used in a chat message.
title: DocumentChatMessageContentRequest
JSONInputRequest:
type: object
properties:
name:
type: string
description: The variable's name
type:
$ref: '#/components/schemas/JsonEnum'
value:
oneOf:
- description: Any type
- type: 'null'
required:
- name
- type
- value
description: A user input representing a JSON object
title: JSONInputRequest
MLModelUsage:
type: object
properties:
output_token_count:
type:
- integer
- 'null'
input_token_count:
type:
- integer
- 'null'
input_char_count:
type:
- integer
- 'null'
output_char_count:
type:
- integer
- 'null'
compute_nanos:
type:
- integer
- 'null'
cache_creation_input_tokens:
type:
- integer
- 'null'
cache_read_input_tokens:
type:
- integer
- 'null'
title: MLModelUsage
UnitEnum:
type: string
enum:
- USD
description: '* `USD` - USD'
title: UnitEnum
ExecutePromptStreamRequest:
type: object
properties:
inputs:
type: array
items:
$ref: '#/components/schemas/PromptDeploymentInputRequest'
description: A list consisting of the Prompt Deployment's input variables and their values.
prompt_deployment_id:
type:
- string
- 'null'
format: uuid
description: The ID of the Prompt Deployment. Must provide either this or prompt_deployment_name.
prompt_deployment_name:
type:
- string
- 'null'
description: The unique name of the Prompt Deployment. Must provide either this or prompt_deployment_id.
release_tag:
type:
- string
- 'null'
description: Optionally specify a release tag if you want to pin to a specific release of the Prompt Deployment
external_id:
type:
- string
- 'null'
description: Optionally include a unique identifier for tracking purposes. Must be unique within a given Workspace.
expand_meta:
oneOf:
- $ref: '#/components/schemas/PromptDeploymentExpandMetaRequest'
- type: 'null'
description: An optionally specified configuration used to opt in to including additional metadata about this prompt execution in the API response. Corresponding values will be returned under the `meta` key of the API response.
raw_overrides:
oneOf:
- $ref: '#/components/schemas/RawPromptExecutionOverridesRequest'
- type: 'null'
description: Overrides for the raw API request sent to the model host. Combined with `expand_raw`, it can be used to access new features from models.
expand_raw:
type:
- array
- 'null'
items:
type: string
description: A list of keys whose values you'd like to directly return from the JSON response of the model provider. Useful if you need lower-level info returned by model providers that Vellum would otherwise omit. Corresponding key/value pairs will be returned under the `raw` key of the API response.
metadata:
type:
- object
- 'null'
additionalProperties:
description: Any type
description: Arbitrary JSON metadata associated with this request. Can be used to capture additional monitoring data such as user id, session id, etc. for future analysis.
required:
- inputs
title: ExecutePromptStreamRequest
ArrayChatMessageContentRequest:
type: object
properties:
type:
$ref: '#/components/schemas/ArrayEnum'
value:
type: array
items:
$ref: '#/components/schemas/ArrayChatMessageContentItemRequest'
required:
- type
- value
description: A list of chat message content items.
title: ArrayChatMessageContentRequest
StringChatMessageContentRequest:
type: object
properties:
type:
$ref: '#/components/schemas/StringEnum'
value:
type: string
required:
- type
- value
description: A string value that is used in a chat message.
title: StringChatMessageContentRequest
RejectedEnum:
type: string
enum:
- REJECTED
title: RejectedEnum
VellumAudioRequest:
type: object
properties:
src:
type: string
description: "The reference to the source data. This can be one of the following formats:\n1. A base64-encoded data URL (e.g., 'data:application/pdf;base64,JVBERi0xLjQKJcfs...').\n2. A url pointing to a file accessible over HTTP or HTTPS.\n3. A reference to a file that's been previously uploaded to Vellum, in the form of 'vellum:uploaded-file:{uploaded_file_id}'.\n You can use the Uploaded Files API to retrieve the url of the uploaded file given its ID. See https://docs.vellum.ai/developers/client-sdk/uploaded-files/retrieve for details."
metadata:
type:
- object
- 'null'
additionalProperties:
description: Any type
required:
- src
title: VellumAudioRequest
StringVellumValue:
type: object
properties:
type:
$ref: '#/components/schemas/StringEnum'
value:
type:
- string
- 'null'
required:
- type
- value
description: A value representing a string.
title: StringVellumValue
ChatMessageRole:
type: string
enum:
- SYSTEM
- ASSISTANT
- USER
- FUNCTION
description: '* `SYSTEM` - System
* `ASSISTANT` - Assistant
* `USER` - User
* `FUNCTION` - Function'
title: ChatMessageRole
FulfilledExecutePromptEvent:
type: object
properties:
state:
$ref: '#/components/schemas/FulfilledEnum'
outputs:
type: array
items:
$ref: '#/components/schemas/PromptOutput'
execution_id:
type: string
meta:
$ref: '#/components/schemas/FulfilledPromptExecutionMeta'
chat_message_metadata:
type:
- object
- 'null'
additionalProperties:
description: Any type
required:
- state
- outputs
- execution_id
description: The final data event returned indicating that the stream has ended and all final resolved values from the model can be found.
title: FulfilledExecutePromptEvent
AudioChatMessageContentRequest:
type: object
properties:
type:
$ref: '#/components/schemas/AudioEnum'
value:
$ref: '#/components/schemas/VellumAudioRequest'
required:
- type
- value
description: An audio value that is used in a chat message.
title: AudioChatMessageContentRequest
ChatHistoryEnum:
type: string
enum:
- CHAT_HISTORY
title: ChatHistoryEnum
FunctionCallVellumValue:
type: object
properties:
type:
$ref: '#/components/schemas/FunctionCallEnum'
value:
oneOf:
- $ref: '#/components/schemas/FunctionCall'
- type: 'null'
required:
- type
- value
description: A value representing a Function Call.
title: FunctionCallVellumValue
StreamingExecutePromptEvent:
type: object
properties:
state:
$ref: '#/components/schemas/StreamingEnum'
output:
$ref: '#/components/schemas/PromptOutput'
output_index:
type: integer
execution_id:
type: string
meta:
$ref: '#/components/schemas/StreamingPromptExecutionMeta'
raw:
type: object
additionalProperties:
description: Any type
description: The subset of the raw response from the model that the request opted into with `expand_raw`.
required:
- state
- output
- output_index
- execution_id
description: The data returned for each delta during the prompt execution stream.
title: StreamingExecutePromptEvent
AudioInputRequest:
type: object
properties:
name:
type: string
description: The variable's name
type:
$ref: '#/components/schemas/AudioEnum'
value:
$ref: '#/components/schemas/VellumAudioRequest'
required:
- name
- type
- value
description: A user input representing a Vellum Audio value
title: AudioInputRequest
PromptOutput:
oneOf:
- $ref: '#/components/schemas/StringVellumValue'
- $ref: '#/components/schemas/JsonVellumValue'
- $ref: '#/components/schemas/ErrorVellumValue'
- $ref: '#/components/schemas/FunctionCallVellumValue'
- $ref: '#/components/schemas/ThinkingVellumValue'
title: PromptOutput
ArrayEnum:
type: string
enum:
- ARRAY
title: ArrayEnum
ArrayChatMessageContentItemRequest:
oneOf:
- $ref: '#/components/schemas/StringChatMessageContentRequest'
- $ref: '#/components/schemas/FunctionCallChatMessageContentRequest'
- $ref: '#/components/schemas/AudioChatMessageContentRequest'
- $ref: '#/components/schemas/VideoChatMessageContentRequest'
- $ref: '#/components/schemas/ImageChatMessageContentRequest'
- $ref: '#/components/schemas/DocumentChatMessageContentRequest'
title: ArrayChatMessageContentItemRequest
StringInputRequest:
type: object
properties:
name:
type: string
description: The variable's name
type:
$ref: '#/components/schemas/StringEnum'
value:
type: string
required:
- name
- type
- value
description: A user input representing a string value
title: StringInputRequest
RejectedExecutePromptEvent:
type: object
properties:
state:
$ref: '#/components/schemas/RejectedEnum'
error:
$ref: '#/components/schemas/VellumError'
execution_id:
type: string
meta:
$ref: '#/components/schemas/RejectedPromptExecutionMeta'
required:
- state
- error
- execution_id
description: The final data returned indicating an error occurred during the stream.
title: RejectedExecutePromptEvent
InitiatedPromptExecutionMeta:
type: object
properties:
model_name:
type:
- string
- 'null'
latency:
type:
- integer
- 'null'
deployment_release_tag:
type:
- string
- 'null'
prompt_version_id:
type:
- string
- 'null'
description: The subset of the metadata tracked by Vellum during prompt execution that the request opted into with `expand_meta`.
title: InitiatedPromptExecutionMeta
FunctionCallEnum:
type: string
enum:
- FUNCTION_CALL
title: FunctionCallEnum
JsonVellumValue:
type: object
properties:
type:
$ref: '#/components/schemas/JsonEnum'
value:
oneOf:
- description: Any type
- type: 'null'
required:
- type
- value
description: A value representing a JSON object.
title: JsonVellumValue
VellumVideoRequest:
type: object
properties:
src:
type: string
description: "The reference to the source data. This can be one of the following formats:\n1. A base64-encoded data URL (e.g., 'data:application/pdf;base64,JVBERi0xLjQKJcfs...').\n2. A url pointing to a file accessible over HTTP or HTTPS.\n3. A reference to a file that's been previously uploaded to Vellum, in the form of 'vellum:uploaded-file:{uploaded_file_id}'.\n You can use the Uploaded Files API to retrieve the url of the uploaded file given its ID. See https://docs.vellum.ai/developers/client-sdk/uploaded-files/retrieve for details."
metadata:
type:
- object
- 'null'
additionalProperties:
description: Any type
required:
- src
title: VellumVideoRequest
RejectedPromptExecutionMeta:
type: object
properties:
latency:
type:
- integer
- 'null'
finish_reason:
oneOf:
- $ref: '#/components/schemas/FinishReasonEnum'
- type: 'null'
description: The subset of the metadata tracked by Vellum during prompt execution that the request opted into with `expand_meta`.
title: RejectedPromptExecutionMeta
ErrorVellumValue:
type: object
properties:
type:
$ref: '#/components/schemas/ErrorEnum'
value:
oneOf:
- $ref: '#/components/schemas/VellumError'
- type: 'null'
required:
- type
- value
description: A value representing an Error.
title: ErrorVellumValue
VideoEnum:
type: string
enum:
- VIDEO
title: VideoEnum
ImageInputRequest:
type: object
properties:
name:
type: string
description: The variable's name
type:
$ref: '#/components/schemas/ImageEnum'
value:
$ref: '#/components/schemas/VellumImageRequest'
required:
- name
- type
- value
description: A user input representing a Vellum Image value
title: ImageInputRequest
ThinkingEnum:
type: string
enum:
- THINKING
title: ThinkingEnum
PromptDeploymentExpandMetaRequest:
type: object
properties:
model_name:
type:
- boolean
- 'null'
description: If enabled, the response will include the model identifier representing the ML Model invoked by the Prompt.
usage:
type:
- boolean
- 'null'
description: If enabled, the response will include model host usage tracking. This may increase latency for some model hosts.
cost:
type:
- boolean
- 'null'
description: If enabled, the response will include model host cost tracking. This may increase latency for some model hosts.
finish_reason:
type:
- boolean
- 'null'
description: If enabled, the response will include the reason provided by the model for why the execution finished.
latency:
type:
- boolean
- 'null'
description: If enabled, the response will include the time in nanoseconds it took to execute the Prompt Deployment.
deployment_release_tag:
type:
- boolean
- 'null'
description: If enabled, the response will include the release tag of the Prompt Deployment.
prompt_version_id:
type:
- boolean
- 'null'
description: If enabled, the response will include the ID of the Prompt Version backing the deployment.
title: PromptDeploymentExpandMetaRequest
FulfilledEnum:
type: string
enum:
- FULFILLED
title: FulfilledEnum
VellumDocumentRequest:
type: object
properties:
src:
type: string
description: "The reference to the source data. This can be one of the following formats:\n1. A base64-encoded data URL (e.g., 'data:application/pdf;base64,JVBERi0xLjQKJcfs...').\n2. A url pointing to a file accessible over HTTP or HTTPS.\n3. A reference to a file that's been previously uploaded to Vellum, in the form of 'vellum:uploaded-file:{uploaded_file_id}'.\n You can use the Uploaded Files API to retrieve the url of the uploaded file given its ID. See https://docs.vellum.ai/developers/client-sdk/uploaded-files/retrieve for details."
metadata:
type:
- object
- 'null'
additionalProperties:
description: Any type
required:
- src
title: VellumDocumentRequest
FunctionCallChatMessageContentValueRequest:
type: object
properties:
name:
type: string
arguments:
type: object
additionalProperties:
description: Any type
id:
type:
- string
- 'null'
required:
- name
- arguments
description: The final resolved function call value.
title: FunctionCallChatMessageContentValueRequest
ImageEnum:
type: string
enum:
- IMAGE
title: ImageEnum
VellumImageRequest:
type: object
properties:
src:
type: string
description: "The reference to the source data. This can be one of the following formats:\n1. A base64-encoded data URL (e.g., 'data:application/pdf;base64,JVBERi0xLjQKJcfs...').\n2. A url pointing to a file accessible over HTTP or HTTPS.\n3. A reference to a file that's been previously uploaded to Vellum, in the form of 'vellum:uploaded-file:{uploaded_file_id}'.\n You can use the Uploaded Files API to retrieve the url of the uploaded file given its ID. See https://docs.vellum.ai/developers/client-sdk/uploaded-files/retrieve for details."
metadata:
type:
- object
- 'null'
additionalProperties:
description: Any type
required:
- src
title: VellumImageRequest
Price:
type: object
properties:
value:
type: number
format: double
unit:
$ref: '#/components/schemas/UnitEnum'
required:
- value
- unit
title: Price
StreamingPromptExecutionMeta:
type: object
properties:
latency:
type:
- integer
- 'null'
description: The subset of the metadata tracked by Vellum during prompt execution that the request opted into with `expand_meta`.
title: StreamingPromptExecutionMeta
JsonEnum:
type: string
enum:
- JSON
title: JsonEnum
ChatMessageContentRequest:
oneOf:
- $ref: '#/components/schemas/StringChatMessageContentRequest'
- $ref: '#/components/schemas/FunctionCallChatMessageContentRequest'
- $ref: '#/components/schemas/ArrayChatMessageContentRequest'
- $ref: '#/components/schemas/AudioChatMessageContentRequest'
- $ref: '#/components/schemas/VideoChatMessageContentRequest'
- $ref: '#/components/schemas/ImageChatMessageContentRequest'
- $ref: '#/components/schemas/DocumentChatMessageContentRequest'
title: ChatMessageContentRequest
VideoInputRequest:
type: object
properties:
name:
type: string
description: The variable's name
type:
$ref: '#/components/schemas/VideoEnum'
value:
$ref: '#/components/schemas/VellumVideoRequest'
required:
- name
- type
- value
description: A user input representing a Vellum Video value
title: VideoInputRequest
ChatMessageRequest:
type: object
properties:
text:
type:
- string
- 'null'
role:
$ref: '#/components/schemas/ChatMessageRole'
content:
oneOf:
- $ref: '#/components/schemas/ChatMessageContentRequest'
- type: 'null'
source:
type:
- string
- 'null'
description: An optional identifier representing who or what generated this message.
metadata:
type:
- object
- 'null'
additionalProperties:
description: Any type
required:
- role
title: ChatMessageRequest
FinishReasonEnum:
type: string
enum:
- LENGTH
- STOP
- UNKNOWN
description: '* `LENGTH` - LENGTH
* `STOP` - STOP
* `UNKNOWN` - UNKNOWN'
title: FinishReasonEnum
ChatHistoryInputRequest:
type: object
properties:
name:
type: string
description: The variable's name, as defined in the deployment.
type:
$ref: '#/components/schemas/ChatHistoryEnum'
value:
type: array
items:
$ref: '#/components/schemas/ChatMessageRequest'
required:
- name
- type
- value
description: A user input representing a list of chat messages
title: ChatHistoryInputRequest
AudioEnum:
type: string
enum:
- AUDIO
title: AudioEnum
ImageChatMessageContentRequest:
type: object
properties:
type:
$ref: '#/components/schemas/ImageEnum'
value:
$ref: '#/components/schemas/VellumImageRequest'
required:
- type
- value
description: An image value that is used in a chat message.
title: ImageChatMessageContentRequest
ExecutePromptEvent:
oneOf:
- $ref: '#/components/schemas/InitiatedExecutePromptEvent'
- $ref: '#/components/schemas/StreamingExecutePromptEvent'
- $ref: '#/components/schemas/FulfilledExecutePromptEvent'
- $ref: '#/components/schemas/RejectedExecutePromptEvent'
title: ExecutePromptEvent
VellumError:
type: object
properties:
code:
$ref: '#/components/schemas/VellumErrorCodeEnum'
message:
type: string
raw_data:
type:
- object
- 'null'
additionalProperties:
description: Any type
required:
- code
- message
title: VellumError
StreamingEnum:
type: string
enum:
- STREAMING
title: StreamingEnum
StringEnum:
type: string
enum:
- STRING
title: StringEnum
ErrorEnum:
type: string
enum:
- ERROR
title: ErrorEnum
FunctionCall:
type: object
properties:
arguments:
type: object
additionalProperties:
description: Any type
id:
type:
- string
- 'null'
name:
type: string
required:
- arguments
- name
description: The final resolved function call value.
title: FunctionCall
FulfilledPromptExecutionMeta:
type: object
properties:
latency:
type:
- integer
- 'null'
finish_reason:
oneOf:
- $ref: '#/components/schemas/FinishReasonEnum'
- type: 'null'
usage:
oneOf:
- $ref: '#/components/schemas/MLModelUsage'
- type: 'null'
cost:
oneOf:
- $ref: '#/components/schemas/Price'
- type: 'null'
description: The subset of the metadata tracked by Vellum during prompt execution that the request opted into with `expand_meta`.
title: FulfilledPromptExecutionMeta
PromptDeploymentInputRequest:
oneOf:
- $ref: '#/components/schemas/StringInputRequest'
- $ref: '#/components/schemas/JSONInputRequest'
- $ref: '#/components/schemas/ChatHistoryInputRequest'
- $ref: '#/components/schemas/AudioInputRequest'
- $ref: '#/components/schemas/VideoInputRequest'
- $ref: '#/components/schemas/ImageInputRequest'
- $ref: '#/components/schemas/DocumentInputRequest'
title: PromptDeploymentInputRequest
InitiatedExecutePromptEvent:
type: object
properties:
state:
$ref: '#/components/schemas/InitiatedEnum'
meta:
$ref: '#/components/schemas/InitiatedPromptExecutionMeta'
execution_id:
type: string
required:
- state
- execution_id
description: The initial data returned indicating that the response from the model has returned and begun streaming.
title: InitiatedExecutePromptEvent
RawPromptExecutionOverridesRequest:
type: object
properties:
body:
type:
- object
- 'null'
additionalProperties:
description: Any type
headers:
type:
- object
- 'null'
additionalProperties:
type: string
description: The raw headers to send to the model host.
url:
type:
- string
- 'null'
description: The raw URL to send to the model host.
title: RawPromptExecutionOverridesRequest
DocumentEnum:
type: string
enum:
- DOCUMENT
title: DocumentEnum
VellumErrorCodeEnum:
type: string
enum:
- INVALID_REQUEST
- INVALID_INPUTS
- PROVIDER_ERROR
- PROVIDER_CREDENTIALS_UNAVAILABLE
- INTEGRATION_CREDENTIALS_UNAVAILABLE
- REQUEST_TIMEOUT
- INTERNAL_SERVER_ERROR
- USER_DEFINED_ERROR
- WORKFLOW_CANCELLED
- NODE_CANCELLED
- PROVIDER_QUOTA_EXCEEDED
- CHAT_QUOTA_EXCEEDED
description: '* `INVALID_REQUEST` - INVALID_REQUEST
* `INVALID_INPUTS` - INVALID_INPUTS
* `PROVIDER_ERROR` - PROVIDER_ERROR
* `PROVIDER_CREDENTIALS_UNAVAILABLE` - PROVIDER_CREDENTIALS_UNAVAILABLE
* `INTEGRATION_CREDENTIALS_UNAVAILABLE` - INTEGRATION_CREDENTIALS_UNAVAILABLE
* `REQUEST_TIMEOUT` - REQUEST_TIMEOUT
* `INTERNAL_SERVER_ERROR` - INTERNAL_SERVER_ERROR
* `USER_DEFINED_ERROR` - USER_DEFINED_ERROR
* `WORKFLOW_CANCELLED` - WORKFLOW_CANCELLED
* `NODE_CANCELLED` - NODE_CANCELLED
* `PROVIDER_QUOTA_EXCEEDED` - PROVIDER_QUOTA_EXCEEDED
* `CHAT_QUOTA_EXCEEDED` - CHAT_QUOTA_EXCEEDED'
title: VellumErrorCodeEnum
FunctionCallChatMessageContentRequest:
type: object
properties:
type:
$ref: '#/components/schemas/FunctionCallEnum'
value:
$ref: '#/components/schemas/FunctionCallChatMessageContentValueRequest'
required:
- type
- value
description: A function call value that is used in a chat message.
title: FunctionCallChatMessageContentRequest
ExecutePromptApiErrorResponse:
type: object
properties:
detail:
type: string
description: Details about why the request failed.
raw_data:
type:
- object
- 'null'
additionalProperties:
description: Any type
description: The raw error data structure, if available.
required:
- detail
title: ExecutePromptApiErrorResponse
InitiatedEnum:
type: string
enum:
- INITIATED
title: InitiatedEnum
DocumentInputRequest:
type: object
properties:
name:
type: string
description: The variable's name
type:
$ref: '#/components/schemas/DocumentEnum'
value:
$ref: '#/components/schemas/VellumDocumentRequest'
required:
- name
- type
- value
description: A user input representing a Vellum Document value
title: DocumentInputRequest
ThinkingVellumValue:
type: object
properties:
type:
$ref: '#/components/schemas/ThinkingEnum'
value:
oneOf:
- $ref: '#/components/schemas/StringVellumValue'
- type: 'null'
required:
- type
- value
description: A value representing Thinking mode output.
title: ThinkingVellumValue
VideoChatMessageContentRequest:
type: object
properties:
type:
$ref: '#/components/schemas/VideoEnum'
value:
$ref: '#/components/schemas/VellumVideoRequest'
required:
- type
- value
description: A video value that is used in a chat message.
title: VideoChatMessageContentRequest
securitySchemes:
default:
type: apiKey
in: header
name: X-API-KEY