Create a chat completion via a Verlon gate

curl --request POST \
  --url https://api.verlon.ai/v3/chat \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "gateId": "<string>",
  "data": {
    "messages": [
      "<unknown>"
    ],
    "vars": {}
  },
  "model": "<string>",
  "metadata": "<unknown>",
  "endUserId": "<string>",
  "sessionId": "<string>"
}
'

{
  "error": "<string>",
  "message": "<string>",
  "details": "<unknown>"
}

Chat

Create a chat completion via a Verlon gate

Use when: caller wants a chat completion (multi-turn or single-prompt) routed through a Verlon gate with automatic provider failover, quality scoring, and usage tracking

Routes a chat completion request through the named Verlon gate. The gate decides which underlying model+provider serves the request based on its current configuration (primary model, fallback chain, parameter overrides). Supports both streaming and non-streaming responses. Verlon handles provider auth, billing, observability, and fallback on failure.

POST

chat

curl --request POST \
  --url https://api.verlon.ai/v3/chat \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "gateId": "<string>",
  "data": {
    "messages": [
      "<unknown>"
    ],
    "vars": {}
  },
  "model": "<string>",
  "metadata": "<unknown>",
  "endUserId": "<string>",
  "sessionId": "<string>"
}
'

{
  "error": "<string>",
  "message": "<string>",
  "details": "<unknown>"
}

Authorizations

Authorization

string

header

required

Verlon API key (prefixed verlon_; legacy keys prefixed layer_ from before the 2026-05 rename also validate). Generated from the dashboard under Settings → API Keys, or via verlon key create in the CLI (legacy verlon key create still works as a bin alias until 2026-06-20).

Body

application/json

gateId

string

required

data

object

required

Show child attributes

model

string

metadata

any

endUserId

string

sessionId

string

Response

Chat completion response. Shape matches the underlying provider format selected by the gate (OpenAI-compatible by default). For streaming requests, returns SSE chunks instead of a single JSON body.

API Keys Management Generate an image via a Verlon gate

Documentation Index

Authorizations

Body

Response