Telnyx Assistants API is one of 169 APIs that Telnyx publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
Tagged areas include Assistants. The published artifact set on APIs.io includes an OpenAPI specification and API documentation.
This API exposes
45 operations
across 26 paths,
and defines 97 schemas.
It is described by OpenAPI 3.2.0, at version 2.0.0.
Requests are made against a single base URL, https://api.telnyx.com/v2.
The identity and technical contract details declared by the specification.
AssistantTools
array
Deprecated for new integrations. Inline tool definitions available to the assistant. Prefer toolids to attach shared tools created with the AI Tools endpoints.
PromptSyncStatus
string
Whether to auto-publish the assistant's instructions as a Langfuse prompt. When ENABLED + promptname set, every assistant create/update pushes instructions to…
TelephonySettings
object
9 properties
Observability
object
8 properties
RetrievalTool
object
2 properties
2 required
CreateScheduledEventRequest
object
9 properties
4 required
ExternalLLM
object
7 properties
2 required
AssistantSmsChatResponse
object
1 property
PaginatedAssistantTestList
object
Paginated list of assistant tests with metadata. Returns a subset of tests based on pagination parameters along with metadata for implementing pagination contr…
2 properties
2 required
PostConversationSettings
object
Configuration for post-conversation processing. When enabled, the assistant receives one additional LLM turn after the conversation ends, allowing it to execut…
1 property
SharedToolResponse
object
6 properties
3 required
ImportMetadata
object
2 properties
AudioVisualizerConfig
object
2 properties
ObservabilityReq
object
8 properties
UpdateAssistantRequest
object
28 properties
HTTPValidationError
object
1 property
ValidationError
object
3 properties
3 required
TestRunResponse
object
Response model containing test run execution details and results. Provides comprehensive information about a test execution including status, timing, logs, and…
12 properties
5 required
inference-embedding_InterruptionSettings
object
Settings for interruptions and how the assistant decides the user has finished speaking. These timings are most relevant when using non turn-taking transcripti…
3 properties
Rule-Output
object
A targeting rule: match clauses (AND) gate serve. An empty match is a catch-all (always fires).
2 properties
1 required
TestSuitesResponse
object
Response containing all available test suite names. Returns a list of distinct test suite names that can be used for filtering and organizing tests.
1 property
1 required
SkipTurnToolParams
object
1 property
UpdateAssistantRequestWithPromotion
inference-embedding_WebhookTool
object
2 properties
2 required
TestWebhookToolResponse
object
Response model for webhook tool test results
5 properties
5 required
SIPReferTool
object
2 properties
2 required
ObservabilityStatus
string
AssistantChatReq
object
3 properties
2 required
TelnyxConversationChannel
string
AssistantIntegration
object
Reference to a connected integration attached to an assistant. Discover available integrations with /ai/integrations and connected integrations with /ai/integr…
2 properties
1 required
ConversationChannelType
string
UpdateAssistantTestRequest
object
Request model for updating an existing assistant test. All fields are optional, allowing partial updates of test configuration. Only provided fields will be up…
8 properties
SendMessageTool
object
The sendmessage tool allows the assistant to send SMS or MMS messages to the end user. The 'to' and 'from' addresses are automatically determined from the conv…
2 properties
2 required
ExternalLLMReq
object
7 properties
2 required
Serve
object
What a rule serves when matched. Exactly one of: - versionid — serve a specific version - rollout — weighted random across versions; weights must sum to less t…
2 properties
TranscriptionSettingsConfig
object
9 properties
ImportAssistantsRequest
object
3 properties
2 required
MessagingSettings
object
3 properties
InferenceEmbeddingTransferToolParams
object
6 properties
2 required
UpdateSharedToolRequest
object
Request model for updating a shared tool.
8 properties
TriggerTestSuiteRunsRequest
object
Request model for triggering test suite runs. Optional request body for the trigger test suite runs endpoint.
1 property
InsightSettings
object
1 property
InviteToolConfig
object
4 properties
1 required
AssistantSmsChatReq
object
5 properties
2 required
inference-embedding_TransferTool
object
2 properties
2 required
EnabledFeatures
string
If telephony is enabled, the assistant will be able to make and receive calls. If messaging is enabled, the assistant will be able to send and receive messages.
ScheduledPhoneCallEventResponse
object
20 properties
5 required
RolloutSlot
object
One slot in a percentage rollout.
2 properties
2 required
CreateAssistantRequest
object
27 properties
2 required
HangupToolParams
object
1 property
PostConversationSettingsReq
object
Configuration for post-conversation processing. When enabled, the assistant receives one additional LLM turn after the conversation ends, allowing it to execut…
1 property
DTMFTool
object
2 properties
2 required
StartSpeakingPlan
object
Controls when the assistant starts speaking after the user stops. These thresholds primarily apply to non turn-taking transcription models. For turn-taking mod…
2 properties
TagsResponse
object
1 property
1 required
Meta
object
4 properties
4 required
TestRunDetailResult
object
2 properties
2 required
TranscriptionSettings
object
5 properties
PaginatedScheduledEventList
object
2 properties
2 required
WidgetSettings
object
Configuration settings for the assistant's web widget.
11 properties
ScheduledSmsEventResponse
object
14 properties
6 required
Clause
object
A single attribute/operator/values check. A clause matches when the routing context's value for attribute satisfies operator against any of values.
3 properties
3 required
TestWebhookToolResponseData
object
Response model for webhook tool test results
1 property
1 required
TestWebhookToolRequest
object
Request model for testing a webhook tool
2 properties
CreateSharedToolRequest
object
Request model for creating a shared (org-level) tool.
8 properties
2 required
WebhookToolParams
object
11 properties
3 required
AssistantScheduledCallAttempt
object
One row in callattempts — captures the terminal outcome of a single dispatch.
5 properties
3 required
inference-embedding_Assistant
object
33 properties
5 required
TranscriptionEndpointingPlan
object
Endpointing thresholds used to decide when the user has finished speaking. Applies to non turn-taking transcription models. For deepgram/flux, use transcriptio…
3 properties
AssistantsListData
object
1 property
1 required
BucketIds
object
2 properties
1 required
InviteTool
object
2 properties
2 required
TriggerTestRunRequest
object
Request model for triggering a single test run. Optional request body for the trigger test run endpoint.
1 property
AssistantDeletedResponse
object
Aligns with the OpenAI API: https://platform.openai.com/docs/api-reference/assistants/deleteAssistant
3 properties
3 required
HandoffTool
object
The handoff tool allows the assistant to hand off control of the conversation to another AI assistant. By default, this will happen transparently to the end us…
2 properties
2 required
PrivacySettings
object
1 property
AssistantTestResponse
object
Response model containing complete assistant test information. Returns all test configuration details including evaluation criteria, scheduling, and metadata.…
10 properties
5 required
CreateAssistantTestRequest
object
Request model for creating a new assistant test. This model defines all the required and optional parameters needed to create a comprehensive test for an AI as…
8 properties
4 required
AddTagRequest
object
1 property
1 required
AuthenticationMethod
string
Authentication method used when connecting to the external LLM endpoint.
SIPReferToolParams
object
3 properties
1 required
SharedToolListResponse
object
2 properties
2 required
AssistantMCPServer
object
Reference to an MCP server attached to an assistant. Create and manage MCP servers with the /ai/mcpservers endpoints, then attach them to assistants by ID.
2 properties
1 required
Rule-Input
object
A targeting rule: match clauses (AND) gate serve. An empty match is a catch-all (always fires).
2 properties
1 required
HandoffToolParams
object
2 properties
1 required
FallbackConfig
object
3 properties
ScheduledEventResponse
Union type for different scheduled event response types
CanaryDeployResponse
object
Response shape. Always carries rules (canonical).
4 properties
4 required
FallbackConfigReq
object
3 properties
SkipTurnTool
object
2 properties
2 required
HangupTool
object
2 properties
2 required
TestStatus
string
Represents the lifecycle of a test: - 'pending': Test is waiting to be executed. - 'starting': Test execution is initializing. - 'running': Test is currently e…
CanaryDeployRequest
object
Create/update request body. Accepts: - rules — canonical ordered list of routing rules
1 property
VoiceSettings
object
11 properties
1 required
AssistantChatResponse
object
1 property
1 required
PaginatedTestRunList
object
Paginated list of test runs with metadata. Returns test run execution results with pagination support for handling large numbers of test executions.
2 properties
2 required
The full machine-readable OpenAPI contract behind this narrative.
Other APIs Telnyx publishes across the network.
