How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Need help?

Contact us
Vellum AI

Vellum AI Execute Prompt Stream API

The Execute Prompt Stream API from Vellum AI — 1 operation(s) for execute prompt stream.

Documentation Provider Profile APIs.io OpenAPI GitHub

Vellum AI Execute Prompt Stream API is one of 23 APIs that Vellum AI publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Execute Prompt Stream. The published artifact set on APIs.io includes an OpenAPI specification.

This API exposes 1 operation across 1 path, and defines 65 schemas. It is described by OpenAPI 3.2.0, at version 1.0.0.

Requests are made against 3 base URLs: https://predict.vellum.ai, https://api.vellum.ai, https://documents.vellum.ai.

1 operations 1 paths 65 schemas 1 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
1.0.0
Base URL
https://api.vellum.ai
Authentication
API Key
Resource Areas
1

Authentication & Security 1

Vellum AI Execute Prompt Stream API declares 1 security scheme for authenticating requests. An API key is passed in the header as X-API-KEY (default).

Paths & Operations 1

Across 1 path, the API surfaces 1 operation — 1 POST. Each is listed below with its method, path, parameters, and response codes.

Execute Prompt Stream 1
POST
/v1/execute-prompt-stream
Execute Prompt Stream
execute-prompt-stream 2 params body → 200400403404500

Schemas 65

The contract defines 65 schemas that model the data the API accepts and returns. The most detailed are ExecutePromptStreamRequest (9 properties), MLModelUsage (7 properties), PromptDeploymentExpandMetaRequest (7 properties), StreamingExecutePromptEvent (6 properties). Each schema is shown below with its type and property counts.

DocumentChatMessageContentRequest
object
A document value that is used in a chat message.
2 properties 2 required
JSONInputRequest
object
A user input representing a JSON object
3 properties 3 required
MLModelUsage
object
7 properties
UnitEnum
string
USD - USD
ExecutePromptStreamRequest
object
9 properties 1 required
ArrayChatMessageContentRequest
object
A list of chat message content items.
2 properties 2 required
StringChatMessageContentRequest
object
A string value that is used in a chat message.
2 properties 2 required
RejectedEnum
string
VellumAudioRequest
object
2 properties 1 required
StringVellumValue
object
A value representing a string.
2 properties 2 required
ChatMessageRole
string
SYSTEM - System ASSISTANT - Assistant USER - User FUNCTION - Function
FulfilledExecutePromptEvent
object
The final data event returned indicating that the stream has ended and all final resolved values from the model can be found.
5 properties 3 required
AudioChatMessageContentRequest
object
An audio value that is used in a chat message.
2 properties 2 required
ChatHistoryEnum
string
FunctionCallVellumValue
object
A value representing a Function Call.
2 properties 2 required
StreamingExecutePromptEvent
object
The data returned for each delta during the prompt execution stream.
6 properties 4 required
AudioInputRequest
object
A user input representing a Vellum Audio value
3 properties 3 required
PromptOutput
ArrayEnum
string
ArrayChatMessageContentItemRequest
StringInputRequest
object
A user input representing a string value
3 properties 3 required
RejectedExecutePromptEvent
object
The final data returned indicating an error occurred during the stream.
4 properties 3 required
InitiatedPromptExecutionMeta
object
The subset of the metadata tracked by Vellum during prompt execution that the request opted into with expandmeta.
4 properties
FunctionCallEnum
string
JsonVellumValue
object
A value representing a JSON object.
2 properties 2 required
VellumVideoRequest
object
2 properties 1 required
RejectedPromptExecutionMeta
object
The subset of the metadata tracked by Vellum during prompt execution that the request opted into with expandmeta.
2 properties
ErrorVellumValue
object
A value representing an Error.
2 properties 2 required
VideoEnum
string
ImageInputRequest
object
A user input representing a Vellum Image value
3 properties 3 required
ThinkingEnum
string
PromptDeploymentExpandMetaRequest
object
7 properties
FulfilledEnum
string
VellumDocumentRequest
object
2 properties 1 required
FunctionCallChatMessageContentValueRequest
object
The final resolved function call value.
3 properties 2 required
ImageEnum
string
VellumImageRequest
object
2 properties 1 required
Price
object
2 properties 2 required
StreamingPromptExecutionMeta
object
The subset of the metadata tracked by Vellum during prompt execution that the request opted into with expandmeta.
1 property
JsonEnum
string
ChatMessageContentRequest
VideoInputRequest
object
A user input representing a Vellum Video value
3 properties 3 required
ChatMessageRequest
object
5 properties 1 required
FinishReasonEnum
string
LENGTH - LENGTH STOP - STOP UNKNOWN - UNKNOWN
ChatHistoryInputRequest
object
A user input representing a list of chat messages
3 properties 3 required
AudioEnum
string
ImageChatMessageContentRequest
object
An image value that is used in a chat message.
2 properties 2 required
ExecutePromptEvent
VellumError
object
3 properties 2 required
StreamingEnum
string
StringEnum
string
ErrorEnum
string
FunctionCall
object
The final resolved function call value.
3 properties 2 required
FulfilledPromptExecutionMeta
object
The subset of the metadata tracked by Vellum during prompt execution that the request opted into with expandmeta.
4 properties
PromptDeploymentInputRequest
InitiatedExecutePromptEvent
object
The initial data returned indicating that the response from the model has returned and begun streaming.
3 properties 2 required
RawPromptExecutionOverridesRequest
object
3 properties
DocumentEnum
string
VellumErrorCodeEnum
string
INVALIDREQUEST - INVALIDREQUEST INVALIDINPUTS - INVALIDINPUTS PROVIDERERROR - PROVIDERERROR PROVIDERCREDENTIALSUNAVAILABLE - PROVIDERCREDENTIALSUNAVAILABLE INT…
FunctionCallChatMessageContentRequest
object
A function call value that is used in a chat message.
2 properties 2 required
ExecutePromptApiErrorResponse
object
2 properties 1 required
InitiatedEnum
string
DocumentInputRequest
object
A user input representing a Vellum Document value
3 properties 3 required
ThinkingVellumValue
object
A value representing Thinking mode output.
2 properties 2 required
VideoChatMessageContentRequest
object
A video value that is used in a chat message.
2 properties 2 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

vellum-execute-prompt-stream-api-openapi.yml Raw ↑

Other APIs Vellum AI publishes across the network.

Vellum LLM Platform API
AE Profile APIs.io
Vellum AI Subpackage Deployments API
AE Profile APIs.io
Vellum AI Subpackage Document Indexes API
AE Profile APIs.io
Vellum AI Subpackage Documents API
AE Profile APIs.io
Vellum AI Subpackage Events API
AE Profile APIs.io
Vellum AI Subpackage Folder Entities API
AE Profile APIs.io
Vellum AI Subpackage Sandboxes API
AE Profile APIs.io
Vellum AI Subpackage Test Suite Runs API
AE Profile APIs.io
Vellum AI Subpackage Test Suites API
AE Profile APIs.io
Vellum AI Subpackage Uploaded Files API
AE Profile APIs.io
Vellum AI Subpackage Workflow Deployments API
AE Profile APIs.io
Vellum AI Subpackage Workflow Executions API
AE Profile APIs.io
#Execute Prompt Stream
← Back to V APIs
API Details
ID
vellum:vellum-execute-prompt-stream-api
Base URL
https://api.vellum.ai
Docs
https://docs.vellum.ai
Provider
Vellum AI
APIs.io →  GitHub →
Explore more
All APIs Providers APIs.io Network
Work with this as data

Every API here is available over the API and to AI agents over MCP. APIs is not yet its own endpoint on the v1 API. Reach this content through network search and the tag graph, or the MCP server below.

Installs https://mcp.apievangelist.com/mcp in Claude, Cursor, VS Code and the rest — one button, every client.

MCP tools for apis
4 tools reach this content
  • search_api_evangelistSearch every content type across the network at once.
  • find_relatedThe shared-tag relevance graph — what else covers this.
  • get_tagEverything one tag labels, across all content types.
  • guide_topicPRO — a curated bundle for a topic: area, guidance, rules, papers, stories, services.
All tools & prompts
Call it yourself
curl for this page
Search the network for this 
curl "https://api.apievangelist.com/v1/search?q=vellum-execute-prompt-stream-api&limit=10"
Everything under a tag 
curl "https://api.apievangelist.com/v1/tags/vellum-execute-prompt-stream-api"

Discovery needs no key. Full bodies and the synthesis endpoints are Pro.

Get an API key

Free tier, no email required. Sign in with whichever identity you already have.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have. Your account

Where this information came from

This is an independent, third-party profile of Vellum AI Execute Prompt Stream API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.