Vertesia Interactions API
Interactions define executable GenAI tasks. Use these endpoints to create drafts, inspect and update definitions, publish immutable versions, fork interactions, resolve executable environment and model choices, execute interactions, and export interaction definitions.
Vertesia Interactions API is one of 48 APIs that Vertesia publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
This API exposes 6 JSON Schema definitions.
Tagged areas include Interactions. The published artifact set on APIs.io includes an OpenAPI specification and 6 JSON Schemas.
This API exposes 33 operations across 28 paths, and defines 194 schemas. It is described by OpenAPI 3.2.0, at version 1.6.0-dev.20261019.172735Z.
Requests are made against a single base URL, https://api.{region}.vertesia.io/api/v1.
33 operations
28 paths
194 schemas
2 DELETE14 GET15 POST2 PUT
Metadata
The identity and technical contract details declared by the specification.
Authentication & Security 2
Vertesia Interactions API declares
2 security schemes
for authenticating requests.
It accepts HTTP bearer tokens (bearerAuth).
It supports OAuth 2.0 (OAuth2) using the authorizationCode flow, exposing 33 scopes.
Paths & Operations 33
Across 28 paths, the API surfaces 33 operations — 2 DELETE, 14 GET, 15 POST, 2 PUT. Each is listed below with its method, path, parameters, and response codes.
Interactions 33
Interactions define executable GenAI tasks. Use these endpoints to create drafts, inspect and update definitions, publish immutable versions, fork interactions, resolve executable…
GET
/interaction-configurations/{interactionId}
Get saved code interaction configuration
PUT
/interaction-configurations/{interactionId}
Create or update code interaction configuration
DELETE
/interaction-configurations/{interactionId}
Remove code interaction configuration
GET
/interactions/catalog/sys
List system interactions
GET
/interactions/catalog/apps/{appName}
List app interactions
GET
/interactions/catalog/apps
List all app interactions
GET
/interactions/catalog/stored
List stored catalog interactions
GET
/interactions/catalog/resolve/{interactionId}
Resolve catalog interaction
GET
/interactions
List interactions
POST
/interactions
Create an interaction
GET
/interactions/tags
List interaction tags
POST
/interactions/endpoints
List interaction endpoints
GET
/interactions/versions/{name}
List interaction versions by name
GET
/interactions/resolve/{nameOrId}
Resolve an interaction
POST
/interactions/facets
Compute interaction facets
GET
/interactions/names
List interaction names
POST
/interactions/export
Export interactions
POST
/interactions/improve
Improve prompt content
GET
/interactions/{interactionId}
Retrieve an interaction
PUT
/interactions/{interactionId}
Update an interaction
DELETE
/interactions/{interactionId}
Delete an interaction
GET
/interactions/{interactionId}/versions
List interaction versions
GET
/interactions/{interactionId}/forks
List interaction forks
POST
/interactions/{interactionId}/publish
Publish an interaction
POST
/interactions/{interactionId}/fork
Fork an interaction
POST
/interactions/{interactionId}/generate-interaction
Generate an interaction
POST
/interactions/{interactionId}/generate-test-data
Generate interaction test data
POST
/interactions/{interactionId}/suggest-prompt-improvements
Suggest prompt improvements
POST
/interactions/{interactionId}/execute
Execute an interaction
POST
/execute
Execute an interaction by selector
POST
/execute/async
Execute an interaction asynchronously
POST
/execute/{endpoint}
Execute an interaction by endpoint
POST
/execute/rate-limit/request
Request an interaction rate-limit slot
Schemas 194
The contract defines 194 schemas that model the data the API accepts and returns. The most detailed are AsyncConversationExecutionPayload (50 properties), ConversationState (42 properties), InteractionExecutionResult (33 properties), ExecutionRun (30 properties). Each schema is shown below with its type and property counts.
PromptStatus
string
PromptSegmentDefType
string
ImprovePromptPayload
object
5 properties
3 required
PromptSegmentDef
object
4 properties
1 required
BedrockMistralOptions
object
8 properties
InteractionConfigurationRecord
object
7 properties
6 required
InteractionExecutionConfiguration
object
14 properties
RateLimitRequestResponse
object
1 property
1 required
ExportedPromptTemplateRef
object
A prompt template reduced to the input schema an export carries.
2 properties
1 required
InferenceProfile
object
A reusable environment, model and inference parameter preset. Credentials remain in the environment.
5 properties
1 required
DeleteByIdResult
object
1 property
1 required
InteractionTags
object
3 properties
3 required
ModelSource
string
Source of the resolved model configuration
OpenAiGptImageOptions
object
12 properties
ModelOptions
object
UserChannel
object
1 required
AsyncCompletionMode
string
TwelvelabsPegasusOptions
object
4 properties
OpenAiTranscriptionOptions
object
2 properties
JSONValue
InteractionNameArray
array
FacetSpec
object
2 properties
2 required
InteractionExecutionError
object
5 properties
2 required
RunDataStorageLevel
string
InteractionTagsArray
array
ProcessAgentPhaseReset
object
3 properties
2 required
PromptRole
string
BedrockMantleClaudeOptions
object
12 properties
VertexAIGeminiOptions
object
27 properties
ImageResult
object
2 properties
2 required
ExecutionEnvironmentRef
object
12 properties
8 required
ProcessAgentToolInputContains
object
4 properties
2 required
EmailChannel
object
Email channel configuration with threading support. Used for email-based agent communication.
6 properties
2 required
Modalities
string
ExecutionRunDocRef
object
The run ref is used to identify a run document in the storage
3 properties
3 required
OpenAiImageGenerationOptions
object
12 properties
1 required
TextArtifactReference
object
Reference to text content externalized to agent artifact storage.
6 properties
6 required
VertexAIClaudeOptions
object
12 properties
WorkflowAncestor
object
3 properties
3 required
InteractionsExportPayload
object
3 properties
InteractionForkPayload
object
4 properties
XAIGrokImageOptions
object
6 properties
ConversationVisibility
string
ProcessAgentToolPhase
object
8 properties
3 required
PromptSegmentRef_PromptTemplateRef
object
4 properties
2 required
VertexAIGeminiOmniVideoOptions
object
5 properties
BedrockGptOssOptions
object
9 properties
GeneratedTestDataRecord
object
AgentResourceAction
string
ToolResult
object
8 properties
3 required
CachePolicy
object
4 properties
4 required
OpenAiAudioOptions
object
3 properties
BedrockPalmyraOptions
object
10 properties
AgentSearchScope_Collection
string
Search is scoped to a specific collection.
AsyncExecutionResult
object
3 properties
2 required
NamedInteractionExecutionPayload
object
12 properties
1 required
ToolReference
object
Lightweight tool reference for activity payloads. References tools stored in GCP instead of embedding full tool definitions.
3 properties
3 required
InCodePrompt
object
6 properties
3 required
AgentResourceReference
object
A navigable reference to a resource an agent tool mutated. Tools return these as tool-result metadata (see {@link ToolResultMeta.resources } ); the conversatio…
5 properties
4 required
JSONSchemaProperties
object
BedrockConverseOptions
object
10 properties
VertexAIGrokOptions
object
5 properties
AudioResult
object
9 properties
3 required
InteractionSearchQuery
object
14 properties
AgentResourceType
string
The kinds of Vertesia resource an agent tool can report having created, updated, or deleted. Restricted to resources that have a real detail route to navigate…
GeneratedInteractionPromptTemplate
object
5 properties
5 required
ThoughtsResult
object
2 properties
2 required
AsyncCompletionOptions
object
Options for async completion and/or streaming LLM responses
10 properties
1 required
InferenceProfileSnapshot
object
The selected profile and content revision at execution creation. Effective overrides are recorded in the execution config.
5 properties
4 required
AsyncInteractionExecutionPayload
object
14 properties
2 required
ToolApprovalGrant
object
4 properties
3 required
InteractionRef
object
13 properties
7 required
NumberValueMap
object
ImprovePromptPayloadConfig
object
1 property
1 required
InteractiveChannel
object
Interactive (UI chat) channel configuration. Used for real-time chat interface communication.
1 property
1 required
JSONSchema
object
9 properties
ExecutionRunInteraction
Interaction reference. Stored interactions may be populated as full Interaction documents; in-code interactions are represented as refs whose id is the namespa…
GeneratedInteractionDefinition
object
7 properties
6 required
JsonResult
object
2 properties
2 required
PromptImprovementResponse
object
1 property
1 required
GenerateTestDataPayload
object
3 properties
1 required
AIModel
object
16 properties
3 required
PromptCachePath
string
InteractionEndpointQuery
object
The payload to query the interaction endpoints
11 properties
BedrockAI21Options
object
9 properties
LlmCallType
string
Types of LLM calls in a conversation
GroqOptions
object
8 properties
1 required
InteractionStatus
string
BedrockCohereCommandOptions
object
10 properties
ResolvedRuntimeConfig
object
Resolved runtime configuration for an interaction
5 properties
2 required
AIModelStatus
string
StatelessExecutionOptions
object
10 properties
1 required
OpenAiImageGenerationMask
object
2 properties
CompletionResult
object
1 required
InteractionRefArray
array
InteractionRefWithSchemaArray
array
AzureFoundryChatOptions
object
10 properties
InteractionPublishPayload
object
2 properties
CatalogInteractionRefArray
array
BedrockMantleResponsesOptions
object
9 properties
PendingToolApprovalResults
object
4 properties
4 required
InteractionName
object
An interaction reduced to the fields a name picker needs.
2 properties
2 required
RateLimitRequestPayload
object
8 properties
1 required
PromptSegmentRef_ExportedPromptTemplateRef
object
4 properties
2 required
JSONObject
object
BedrockMantleChatCompletionsOptions
object
8 properties
ResolvedInteractionExecutionInfo
object
Resolved execution info for an interaction. Contains the interaction ID, basic metadata, and the resolved runtime configuration (environment, model) that would…
7 properties
6 required
ThinkingLevel
string
ResolvedEnvironmentInfo
object
Resolved environment information
3 properties
3 required
AgentCheckpointConfiguration
object
2 properties
ProjectRef
object
4 properties
3 required
OpenRouterTextOptions
object
23 properties
ReasoningEffort
string
InteractionVisibility
string
AsyncConversationExecutionPayload
object
50 properties
2 required
SchemaRef
object
Schema can be stored or specified as a reference to an external schema. We only support "store:" references for now
1 property
1 required
InteractionPromptSegmentInput
object
4 properties
1 required
AgentBudgetConfiguration
object
Weighted token budget for an agent run and its subagent workstreams. A call is charged output × outputtokenweight + uncached input × inputtokenweight + cached…
8 properties
ExternalizedToolInputRefs
object
ExecutionRunStatus
string
OpenAiDalleOptions
object
6 properties
InteractionPromptTemplateInput
object
20 properties
12 required
CatalogInteractionRef
object
Reference to an interaction in the catalog. Used in catalog listing. The id is composed of the namespace and the interaction name. Stored interactions can use…
9 properties
5 required
HttpTimeoutOptions
object
HTTP timeouts applied to a driver's upstream LLM-provider calls. All values are in milliseconds. Drivers should map these onto whatever HTTP client their SDK u…
4 properties
BedrockClaudeOptions
object
13 properties
MistralTextOptions
object
14 properties
ConfigModes
string
OpenAiThinkingOptions
object
12 properties
ModelType
string
InferenceProfileName
string
Editable display name, independent of the stable profile ID.
AgentSearchScope
string
Defines the scope for agent search operations.
InteractionConfigurationResult
object
1 property
1 required
AsyncExecutionPayload
object
1 required
OpenAiSpeechOptions
object
5 properties
ToolUse
object
A tool use instance represents a call to a tool. The id property is used to identify the tool call.
4 properties
3 required
ProcessAgentExecutionPolicy
object
11 properties
1 required
ToolDefinition
object
Tool definition for LLM tool use. The inputschema uses a permissive type to support both: - AJV's JSONSchemaType for type-safe schema generation - Plain object…
3 properties
2 required
PromptTemplate
object
20 properties
13 required
ConversationState
object
Conversation state passed between workflow activities: the activity-safe, per-turn dynamic subset of a multi-turn agent conversation. Rides every conversation…
42 properties
5 required
AnthropicClaudeOptions
object
13 properties
ImagenTaskType
string
BedrockNovaOptions
object
9 properties
ExecutionRunWorkflow
object
5 properties
2 required
InteractionExecutionResult
object
33 properties
14 required
InteractionCreatePayload
object
19 properties
3 required
ImagenMaskMode
string
InteractionEndpointArray
array
NovaCanvasOptions
object
13 properties
1 required
VideoResult
object
2 properties
2 required
TextFallbackOptions
object
10 properties
AgentToolApprovalMode
string
StreamingTelemetryContext
object
Telemetry context for streaming mode. Contains info not available in currentstate needed to send LlmCallEvent.
3 properties
2 required
AccountRef
object
2 properties
2 required
StreamingOptions
object
Streaming-specific options (only needed when stream=true)
2 properties
1 required
RunSource
object
5 properties
5 required
ConversationStripOptions
object
Configuration for stripping large data from conversation history to prevent JSON serialization issues and reduce storage bloat.
3 properties
GeneratedInteractionDefinitionArray
array
Interaction
object
29 properties
14 required
ImagenOptions
object
19 properties
GeneratedInteractionPromptSegment
object
2 properties
2 required
InferenceProfileId
string
MongoDB ObjectId of the inference profile.
Plan
object
2 properties
1 required
ResolvedCatalogInteraction
object
A catalog interaction resolved to its complete executable definition.
17 properties
6 required
InteractionEndpoint
object
A description of an interaction endpoint.
12 properties
6 required
PendingMcpConnection
object
An MCP server the user can connect to but hasn't yet (active + accessible, no OAuth token). Built at tool-discovery time and stored on the conversation state s…
5 properties
3 required
GeneratedTestDataRecordArray
array
ToolResultMeta
object
Metadata a tool executor may attach to its result. Kept as an open record for forward compatibility while typing the fields the runtime interprets.
1 property
ResultStorageOptions
object
Options for storing inference results to cloud storage
1 property
1 required
ComputedFacetResponse
object
1 property
UpdateInteractionConfigurationPayload
object
2 properties
1 required
PlanTask
object
5 properties
2 required
SupportedProviders
string
ComputeInteractionFacetPayload
object
2 properties
1 required
ExecutionTokenUsage
object
9 properties
GenerateInteractionPayload
object
2 properties
2 required
ExecutionRun
object
30 properties
14 required
SkillContextTriggers
object
Context triggers for auto-injection of skills. When these conditions match, the skill is automatically injected into the agent context.
3 properties
InteractionRefWithSchema
object
An interaction reference carrying the schemas an export needs to reconstruct it.
14 properties
7 required
ErrorResponse
object
Standard JSON error response returned by the server error handler.
5 properties
2 required
AgentRunnerOptions
object
Configuration options for Agent Runner functionality. These options control how interactions are exposed and executed in the Agent Runner.
11 properties
TextResult
object
2 properties
2 required
InteractionUpdatePayload
object
23 properties
PromptTemplateRef
object
10 properties
7 required
PromptModalities
object
2 properties
2 required
PromptCacheDiagnostic
object
Safe diagnostic for one provider-side explicit prompt-cache attempt. It never contains prompt contents, images, credentials, or full provider resource names.
9 properties
4 required
OpenAiTextOptions
object
16 properties
ToolApprovalGrantMap
object
InitialToolCall
object
A tool invocation executed before the first model turn of a conversation. Results are injected into the initial context so the agent starts with them in hand.
4 properties
2 required
InteractionExecutionPayload
object
11 properties
ExternalizedToolInputRef
object
Sidecar metadata for generated tool input fields that were stored outside model-visible toolinput. Keyed by tooluse.id on ConversationState.
3 properties
3 required
PromptCacheMode
string
TemplateType
string
RunSourceTypes
string
UsedSkill
object
Skill metadata tracked when a skill is used
5 properties
2 required
Specification
The full machine-readable OpenAPI contract behind this narrative.
Source
More from Vertesia 12
Other APIs Vertesia publishes across the network.
Vertesia Access Control Entries API
Vertesia Account API
Vertesia Accounts API
Vertesia Agent Runs API
Vertesia API Keys API
Vertesia Apps API
Vertesia Audit Trail API
Vertesia Bulk Operations API
Vertesia Collections API
Vertesia Commands API
Vertesia Content Object Types API
Vertesia Content Query API
#Interactions
Where this information came from
This is an independent, third-party profile of Vertesia Interactions 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.