AsyncAPI channel · Retell AI · Retell AI WebSocket APIs

`custom_llm/{call_id}`

Custom LLM WebSocket channel. Retell AI opens a connection to the developer's WebSocket server and exchanges JSON messages identified by `interaction_type` (Retell to LLM) or `response_type` (LLM to Retell).

Open source AsyncAPI → All Retell AI channels Retell AI provider profile

Provider: Retell AI AsyncAPI: v2.6.0 Spec: Retell AI WebSocket APIs Operations: 2 Messages: 13

Channel address

custom_llm/{call_id}

Parameters

call_id — Unique identifier of the call.

Operations

publish

llmToRetell

Messages sent from the LLM server to Retell.

retellToLlm

Messages sent from Retell to the LLM server.

Messages

LlmConfig

LLM server-side configuration sent to Retell.

Content-Type: application/json

LlmUpdateAgent

Update agent-level runtime settings.

Content-Type: application/json

LlmPingPong

Heartbeat ping sent from the LLM server to Retell.

Content-Type: application/json

LlmResponse

Streamed agent response chunk.

Content-Type: application/json

LlmAgentInterrupt

Agent-initiated interruption.

Content-Type: application/json

LlmToolCallInvocation

LLM reports a tool / function call invocation.

Content-Type: application/json

LlmToolCallResult

LLM reports the result of a tool / function call.

Content-Type: application/json

LlmMetadata

Custom metadata sent by the LLM server to Retell.

Content-Type: application/json

RetellPingPong

Heartbeat ping sent by Retell to the LLM server.

Content-Type: application/json

RetellCallDetails

Initial call metadata sent by Retell when `call_details` is enabled via the LLM-side config message.

Content-Type: application/json

RetellUpdateOnly

Transcript / turn-taking update that does not require an LLM response.

Content-Type: application/json

RetellResponseRequired

Retell expects the LLM server to produce a response.

Content-Type: application/json

RetellReminderRequired

Retell signals that a reminder response is required after silence.

Content-Type: application/json

About AsyncAPI

The AsyncAPI specification describes event-driven APIs the way OpenAPI describes request/response APIs. A channel is the named pipe — a webhook URL, a Kafka topic, a WebSocket route, an MQTT subject — that producers and consumers publish or subscribe to. Each channel carries one or more messages with structured payloads, and an operation declares whether a given party sends or receives on that channel.

Browse every event-driven channel on the APIs.io network or compare with the broader Agent Skill and MCP server surfaces of the same providers.

Work with this as data

Every channel here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for event channels

4 MCP tools reach this

find_channelsBrowse and filter every channel in the catalog.
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.

All 92 tools →

Call it yourself

curl for this page

This channel

curl "https://apis.io/api/v1/channels/custom-llm-call-id"

All event channels

curl "https://apis.io/api/v1/channels?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

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.

GitHub Google LinkedIn

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