Console

Playground

Compose a request and inspect the payload. Sending it checks the catalog, then stops because no model provider is connected.

Request parameters

ModelTemperature 1.0Max output tokensSystem prompt

Response

Streaming is shown here after a provider is connected.

Responses appear here only after a configured provider accepts the request. This stage does not generate a sample answer.

Code preview

{
  "model": "",
  "temperature": 1,
  "max_output_tokens": 1024,
  "system": "You are a precise assistant.",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}

Request details

Status: Idle
Latency: —
Input tokens: —
Output tokens: —

Token totals stay empty until a completed provider request is metered.

Loading playground…