​

Telnyx AI — Documentation Index

Inference, AI assistants, missions, and LiveKit integrations. One section of the Telnyx developer docs (https://developers.telnyx.com). Root index: https://developers.telnyx.com/llms.txt · Full content for this section: https://developers.telnyx.com/development/llms/ai-llms-full-txt.md

​

Subsections

Focused per-subsection files (index + full content):

• Inference (full)
• Embedding & RAG (full)
• Assistants (full)
• LiveKit on Telnyx (Beta) (full)

​

Inference

• Models: Open-source LLMs available through the Telnyx Inference API, hosted on Telnyx GPUs and accessible via an OpenAI-compatible Chat Completions endpoint.
• Regions & Availability: GPU regions and routing behavior for the Telnyx Inference API, spanning four regions across three continents with automatic nearest-region routing.
• Pricing: Pay-per-token pricing for the Telnyx Inference API with no minimums or commitments. See current per-model rates and available regions.
• Data Residency & Compliance FAQ: How Telnyx handles processing location, storage at rest, self-hosted vs third-party STT/TTS/LLM providers, data retention, and model training across the Inference API and Voice AI Assistants.
• Integrations: Use the OpenAI-compatible Telnyx Inference API with popular AI frameworks by swapping base_url and api_key — works with LangChain, LlamaIndex, and others.
• OpenAI Migration: Migrate from the OpenAI API to the Telnyx Inference API by changing two environment variables and a model name — no code rewrites required.
• Anthropic Migration: Migrate from the Anthropic API to the Telnyx Inference API by changing the base URL and passing your Telnyx API key in an Authorization header — no code rewrites required.
• LangChain: Use Telnyx Inference as an LLM provider in LangChain. Configure ChatOpenAI with the Telnyx base URL to power chains, agents, and retrieval pipelines.
• LlamaIndex: Use Telnyx Inference with LlamaIndex to build RAG applications. Configure the OpenAI-compatible client to index documents and run retrieval-augmented queries.
• CrewAI: Integrate Telnyx Inference with CrewAI to build multi-agent workflows. Use Telnyx as the LLM provider for autonomous agents and crew orchestration.
• LiveKit: Integrate Telnyx STT, TTS, and LLM services into LiveKit agents using the Telnyx LiveKit Plugin.
• Inference API: Quickstart for the Telnyx Inference API. Get an API key, send your first chat completion request, and explore models for text, embeddings, and audio.
• Function Calling: Use function calling with the Telnyx Inference API to let LLMs invoke your tools. Define JSON schemas, handle tool calls, and return structured outputs.
• Streaming and Parallel Calls: Stream tool calls and run multiple functions in parallel with the Telnyx Inference API. Handle partial JSON, deltas, and concurrent tool invocations.
• JSON Mode and Beyond: In this tutorial, you’ll learn how to: Start building on Telnyx today.
• Fine Tuning: Fine-tune open-source models on the Telnyx Inference platform. Upload a training dataset, run a job, and deploy your customized model for inference.
• Audio Language Models: Use Telnyx audio language models for speech-to-text, translation, and audio understanding. Send audio files or streams and receive transcripts and analysis.
• PR Reviewer - Github Action: Telnyx Inference tool for automatically reviewing Pull Requests at GitHub
• AI SMS Outfit Recommender with OpenMeteo: Telnyx Inference + AI offering SMS outfit recommendations using

​

Embedding & RAG

• Overview: Build retrieval, semantic search, and conversation memory with Telnyx.
• Overview: Search persisted conversation history across supported Telnyx communication sources.
• Feature Coverage: Feature coverage for Conversation History.
• Searching: Search persisted conversation records with the Conversation Histories API.
• Retention: Retention behavior for Conversation History.
• Pricing: Pricing information for Conversation History.
• Embeddings: Generate vector embeddings with the Telnyx Inference API for semantic search, clustering, and RAG. Supports multiple embedding models and batch requests.
• Clusters: Group similar documents and discover themes in your data with Telnyx Inference clusters. Run unsupervised clustering on embeddings to surface insights.

​

Assistants

• Voice Assistant: Build a voice AI assistant in the Telnyx portal without writing code. Pick a model and voice, attach a phone number, and start taking inbound calls.
• Multi-Participant Calls: Invite additional participants into a live Voice AI call and control when your assistant should speak or stay silent.
• Memory: Give Telnyx AI Assistants long-term memory so they recall caller details across sessions. Configure memory scope, retrieval, and conversation history.
• Dynamic Variables: Personalize Telnyx AI Assistant prompts with dynamic variables. Pass caller context, account data, and CRM fields at runtime into the assistant instructions.
• Conversation Workflows: Design multi-step Telnyx AI Assistant conversations with workflow nodes, conditional routing, per-step instructions, model and voice overrides, and assistant routing.
• Async Tools: Build responsive Telnyx AI Assistants that keep talking while slow backends run. Use async webhooks and the Add Messages API together or independently.
• Filler Messages: Eliminate dead air during synchronous webhook tool calls by configuring scripted filler phrases that play at timed intervals while your backend processes requests.
• Tools Library: Create tools once and share them across all your AI assistants. Migrate legacy tools at your own pace.
• AI Assistants and Edge Compute: Use a Telnyx Edge Compute function as the backend for dynamic variables and webhook tool calls — no separate server required.
• Client-Side Tools: Let your AI assistant call functions that run in the browser during a conversation. Configure client-side tools in the portal and implement handlers with the Telnyx AI Agent library.
• Agent Handoff: Enable seamless AI-to-AI handoffs with specialized assistants working together in a single conversation, providing expert-level support across multiple domains.
• Voicemail Detection on Transfer: Configure Voice AI Assistants to detect voicemail on transferred calls and respond automatically.
• Scheduled Events: Schedule outbound phone calls and SMS messages from Voice AI Assistants, with configurable retry policies for unanswered calls.
• Transcription Settings: Choose and configure speech-to-text (STT) models for AI Assistants, including Deepgram, Azure, AssemblyAI, xAI, and Parakeet models.
• Integrations: Connect Telnyx AI Assistants with enterprise platforms like Salesforce, HubSpot, ServiceNow, Zendesk, Microsoft Teams, Notion, Stripe, and more to automate workflows during conversations.
• Testing, Versions & Traffic Distribution: A/B test Telnyx AI Assistant versions in production. Split traffic across prompts, models, and voices to measure quality before promoting a new version.
• Importing Assistants: Import AI assistants from OpenAI, ElevenLabs, Vapi, and other providers into Telnyx. Migrate prompts, voices, tools, and knowledge bases in a few steps.
• Custom LLMs for Assistants: Configure Azure OpenAI, AWS Bedrock, Baseten, or any OpenAI-compatible endpoint as a custom LLM provider for your Telnyx AI assistants.
• Voice Outreach: Give your AI agent a mission to research businesses, make phone calls, and report back with results — all tracked and auditable through the Telnyx Missions API.
• Creating insights: Step-by-step guide to creating AI Insights in the Mission Control Portal to analyze your AI Assistant conversations.
• Use cases: Industry-specific examples and implementation patterns for AI Insights across healthcare, customer support, sales, e-commerce, and financial services.
• Structured insights: Create AI Insights with defined JSON schemas for consistent, structured data extraction from conversations.
• Insight groups: Organize AI Insights into reusable groups and configure webhook delivery for automated insights distribution.
• Telnyx-managed insights: Use built-in insights from Telnyx — Agent Instruction Following and User Satisfaction — to measure assistant quality out of the box, no custom configuration needed.

​

LiveKit on Telnyx (Beta)

• Overview: Deploy and run LiveKit agents on Telnyx infrastructure with built-in telephony, STT, TTS, and LLM — all on one platform.
• Compatibility: What works, what’s different, and what’s not available when using LiveKit on Telnyx vs LiveKit Cloud or self-hosted.
• Quick Start: Deploy a LiveKit voice agent on Telnyx in minutes and call it from your phone using a real Telnyx number, with no third-party SIP setup required.
• Connect: Point your existing LiveKit CLI and SDKs at the Telnyx platform by swapping the URL and credentials — no code changes required to migrate.
• From LiveKit Cloud: Switch from LiveKit Cloud to Telnyx — change three environment variables, keep everything else.
• From Self-Hosted: Stop running LiveKit infrastructure. Deploy your agents to Telnyx.
• Build: Build a voice agent with Telnyx STT, TTS, and LLM and deploy it to the Telnyx platform.
• Deploy: Deploy your LiveKit agent to Telnyx infrastructure with the lk agent deploy command, which builds a container image and provisions workers in chosen regions.
• Configuration: Configuration options for deploying LiveKit agents on Telnyx, including regions, runtime settings, autoscaling, and resource provisioning details.
• Secrets: Manage API keys and sensitive configuration values for LiveKit agents deployed on Telnyx, set at deploy time or updated after deployment.
• Management & Access: Understand the access and management model for LiveKit on Telnyx — what you control as the developer and what Telnyx manages on the underlying platform.
• Overview: Overview of STT, TTS, and LLM plugin configuration for Telnyx LiveKit agents, with on-prem inference running on Telnyx GPUs by default.
• STT: Speech-to-text models available through Telnyx for LiveKit voice agents, including Telnyx-hosted Deepgram models running on dedicated GPUs via plugin.
• TTS: TTS models and voices available through Telnyx for LiveKit voice agents.
• LLM: LLM inference for LiveKit voice agents via the Telnyx Inference API — OpenAI-compatible, no concurrency limits, accessible through the standard OpenAI plugin.
• Observability: Monitor LiveKit agents running on Telnyx using built-in agent logs, deployment metrics, and observability tooling available through the dashboard.
• Telephony: Connect Telnyx phone numbers to your LiveKit voice agents with no third-party SIP trunk setup — calls route on-net from Telnyx SIP directly to your agent.
• Architecture: How the Telnyx LiveKit platform works, including agent containers, autoscaling, SIP integration, and AI inference colocated in each region.
• Regions: Available LiveKit regions and platform endpoints on Telnyx, with guidance on selecting the closest deployment region for low-latency agents.
• Limits: Build, runtime, and concurrency limits for LiveKit agents running on Telnyx, including session quotas, resource caps, and storage constraints.
• Pricing: Usage-based pricing for LiveKit on Telnyx, with compute, AI models, and telephony billed on a single invoice with no third-party SIP fees.

​

API Reference (AI)

​

OpenAI Chat

• Create a chat completion (OpenAI-compatible): Chat with a language model. This endpoint is consistent with the OpenAI Chat Completions API and may be used with the OpenAI JS or Python SDK by setting the ba…
• Get available models (OpenAI-compatible): Lists every model currently available to your account on Telnyx Inference, including SOTA open-source LLMs hosted on Telnyx GPUs (for example `moonshotai/Kimi-…
• Create an OpenAI-compatible response: Create a response using Telnyx’s OpenAI-compatible Responses API. This endpoint is compatible with the OpenAI Responses API and may be used with the OpenAI JS…

​

Fine Tuning

• List fine tuning jobs: Retrieve a list of all fine tuning jobs created by the user.
• Create a fine tuning job: Create a new fine tuning job.
• Get a fine tuning job: Retrieve a fine tuning job by job_id.
• Cancel a fine tuning job: Cancel a fine tuning job.

​

Anthropic Messages

• Create a message (Anthropic-compatible): Send a message to a language model using the Anthropic Messages API format. This endpoint is compatible with the Anthropic Messages API and may be used with th…

​

Chat

• Summarize file content: Generate a summary of a file’s contents.

​

Conversation Histories

• Search conversation histories: Performs semantic vector search across conversation history records.

​

Embeddings

• Get Tasks by Status: Retrieve tasks for the user that are either queued, processing, failed, success or partial_success based on the query string. Defaults to queued an…
• Embed documents: Perform embedding on a Telnyx Storage Bucket using the a embedding model.
• List embedded buckets: Get all embedding buckets for a user.
• Get file-level embedding statuses for a bucket: Get all embedded files for a given user bucket, including their processing status.
• Disable AI for an Embedded Bucket: Deletes an entire bucket’s embeddings and disables the bucket for AI-use, returning it to normal storage pricing.
• Search for documents: Perform a similarity search on a Telnyx Storage Bucket, returning the most similar num_docs document chunks to the query.
• Embed URL content: Embed website content from a specified URL, including child pages up to 5 levels deep within the same domain. The process crawls and loads content from the mai…
• Get an embedding task’s status: Check the status of a current embedding task. Will be one of the following:

​

Clusters

• List all clusters
• Compute new clusters: Starts a background task to compute how the data in an embedded storage bucket is clustered. This helps identify common themes and patterns in the data.
• Fetch a cluster
• Delete a cluster
• Fetch a cluster visualization

​

OpenAI Embeddings

• Create embeddings: Creates an embedding vector representing the input text. This endpoint is compatible with the OpenAI Embeddings API and may be used with the OpenAI JS or Pytho…
• List embedding models: Returns a list of available embedding models. This endpoint is compatible with the OpenAI Models API format.

​

Assistants

• List assistants: Retrieve a list of all AI Assistants configured by the user.
• Create an assistant: Create a new AI Assistant.
• Get an assistant: Retrieve an AI Assistant configuration by assistant_id.
• Update an assistant: Update an AI Assistant’s attributes.
• Delete an assistant: Delete an AI Assistant by assistant_id.
• Assistant Chat (BETA): This endpoint allows a client to send a chat message to a specific AI Assistant. The assistant processes the message and returns a relevant reply based on the…
• Assistant Sms Chat: Send an SMS message for an assistant. This endpoint:
• Clone Assistant: Clone an existing assistant, excluding telephony and messaging settings.
• Enhance Assistant Instructions: Enhance an assistant’s instructions using an LLM. The endpoint reads the assistant’s current instructions and tools, then streams back improved instructions as…
• Import assistants from external provider: Import assistants from external providers. Any assistant that has already been imported will be overwritten with its latest version from the importing provider.
• List scheduled events: Get scheduled events for an assistant with pagination and filtering
• Create a scheduled event: Create a scheduled event for an assistant
• Get a scheduled event: Retrieve a scheduled event by event ID
• Delete a scheduled event: If the event is pending, this will cancel the event. Otherwise, this will simply remove the record of the event.
• List assistant tests with pagination: Retrieves a paginated list of assistant tests with optional filtering capabilities
• Create a new assistant test: Creates a comprehensive test configuration for evaluating AI assistant performance
• Get all test suite names: Retrieves a list of all distinct test suite names available to the current user
• Get test suite run history: Retrieves paginated history of test runs for a specific test suite with filtering options
• Trigger test suite execution: Executes all tests within a specific test suite as a batch operation
• Get assistant test by ID: Retrieves detailed information about a specific assistant test
• Update an assistant test: Updates an existing assistant test configuration with new settings
• Delete an assistant test: Permanently removes an assistant test and all associated data
• Get test run history for a specific test: Retrieves paginated execution history for a specific assistant test with filtering options
• Trigger a manual test run: Initiates immediate execution of a specific assistant test
• Get specific test run details: Retrieves detailed information about a specific test run execution
• Get all versions of an assistant: Retrieves all versions of a specific assistant with complete configuration and metadata
• Get a specific assistant version: Retrieves a specific version of an assistant by assistant_id and version_id
• Update a specific assistant version: Updates the configuration of a specific assistant version. Can not update main version
• Delete a specific assistant version: Permanently removes a specific version of an assistant. Can not delete main version
• Promote an assistant version to main: Promotes a specific version to be the main/current version of the assistant. This will delete any existing canary deploy configuration and send all live produc…
• Get Canary Deploy: Endpoint to get a canary deploy configuration for an assistant.
• Create Canary Deploy: Endpoint to create a canary deploy configuration for an assistant.
• Update Canary Deploy: Endpoint to update a canary deploy configuration for an assistant.
• Delete Canary Deploy: Endpoint to delete a canary deploy configuration for an assistant.
• Get assistant texml: Get an assistant texml by assistant_id.
• Test Assistant Tool: Test a webhook tool for an assistant
• Get All Tags
• Add Assistant Tag
• Remove Assistant Tag
• Add Assistant Tool
• Remove Assistant Tool

​

Integrations

• List Integrations: List all available integrations.
• List User Integrations: List user setup integrations
• Get User Integration connection By Id: Get user setup integrations
• Delete Integration Connection: Delete a specific integration connection.
• List Integration By Id: Retrieve integration details

​

MCP Servers

• List MCP Servers: Retrieve a list of MCP servers.
• Create MCP Server: Create a new MCP server.
• Get MCP Server: Retrieve details for a specific MCP server.
• Update MCP Server: Update an existing MCP server.
• Delete MCP Server: Delete a specific MCP server.

​

Missions

• List missions: List all missions for the organization
• Create mission: Create a new mission definition
• List recent events: List recent events across all missions
• List recent runs: List recent runs across all missions
• Get mission: Get a mission by ID (includes tools, knowledge_bases, mcp_servers)
• Update mission: Update a mission definition
• Delete mission: Delete a mission
• Clone mission: Clone an existing mission
• List runs for mission: List all runs for a specific mission
• Start a run: Start a new run for a mission
• Get run details: Get details of a specific run
• Update run: Update run status and/or result
• Cancel run: Cancel a running or paused run
• List events: List events for a run (paginated)
• Log event: Log an event for a run
• Get event details: Get details of a specific event
• Pause run: Pause a running run
• Get plan: Get the plan (all steps) for a run
• Create initial plan: Create the initial plan for a run
• Add step(s) to plan: Add one or more steps to an existing plan
• Get step details: Get details of a specific plan step
• Update step status: Update the status of a plan step
• Resume run: Resume a paused run
• List linked Telnyx agents: List all Telnyx agents linked to a run
• Link Telnyx agent to run: Link a Telnyx AI agent (voice/messaging) to a run
• Unlink Telnyx agent: Unlink a Telnyx agent from a run
• List knowledge bases: List all knowledge bases for a mission
• Create knowledge base: Create a new knowledge base for a mission
• Get knowledge base: Get a specific knowledge base by ID
• Update knowledge base: Update a knowledge base definition
• Delete knowledge base: Delete a knowledge base from a mission
• List MCP servers: List all MCP servers for a mission
• Create MCP server: Create a new MCP server for a mission
• Get MCP server: Get a specific MCP server by ID
• Update MCP server: Update an MCP server definition
• Delete MCP server: Delete an MCP server from a mission
• List tools: List all tools for a mission
• Create tool: Create a new tool for a mission
• Get tool: Get a specific tool by ID
• Update tool: Update a tool definition
• Delete tool: Delete a tool from a mission

​

Conversations

• List conversations: Retrieve a list of all AI conversations configured by the user. Supports PostgREST-style query parameters for filtering. Examples are included for the standard…
• Create a conversation: Create a new AI Conversation.
• Aggregate Conversation Insights: Aggregate conversation insights by specified fields
• Get Insight Template Groups: Get all insight groups
• Create Insight Template Group: Create a new insight group
• Get Insight Template Group: Get insight group by ID
• Update Insight Template Group: Update an insight template group
• Delete Insight Template Group: Delete insight group by ID
• Assign Insight Template To Group: Assign an insight to a group
• Unassign Insight Template From Group: Remove an insight from a group
• Get Insight Templates: Get all insights
• Create Insight Template: Create a new insight
• Get Insight Template: Get insight by ID
• Update Insight Template: Update an insight template
• Delete Insight Template: Delete insight by ID
• Get a conversation: Retrieve a specific AI conversation by its ID.
• Update conversation metadata: Update metadata for a specific conversation.
• Delete a conversation: Delete a specific conversation by its ID.
• Get insights for a conversation: Retrieve insights for a specific conversation
• Create Message: Add a new message to the conversation. Used to insert a new messages to a conversation manually ( without using chat endpoint )
• Get conversation messages: Retrieve messages for a specific conversation, including tool calls made by the assistant.