Requests

Send the model and messages your application would normally send.

POST /v1/chat/completions

{
  "model": "YOUR_MODEL",
  "messages": [
    {
      "role": "user",
      "content": "Explain what this function does: function add(a, b) { return a + b; }"
    }
  ]
}

Field	Purpose
`model`	The requested model identifier.
`messages`	The conversation in the model API’s usual message format.
`stream`	Set to `true` to request a streamed response.
`tools`	Your usual tool definitions, when supported by the selected model.
Other model parameters	Use the parameters supported by your model and configured API format.

Messages

Include instructions, user messages and the conversation history needed for the next answer. For tool use, include tool definitions and tool-result messages in the usual model format. tlc handles its processing behind this request.

GET /v1/models

The gateway forwards the model-list request to its configured upstream. Model names and availability come from that provider.

The Transductor is in early access. Join the waitlist.