Playground

Test an OpenAI-compatible chat request, inspect usage, and copy starter code for the selected model.

Request

Model

OnlineOpenAI1M context32K max output

System prompt

User message

Prompt and response payloads are not retained by default; debug log controls stay behind the operator rollout.

Temperature 0.7

Max tokens

Stream responseDisabled

Response

Ready

Send a request to generate a response, request ID, token usage, and estimated cost.

Prompt tokens

Completion tokens

Total tokens

Estimated cost

Code examples

openai/gpt-4.1-mini

curl https://api.wlrouter.com/v1/chat/completions \
  -H "Authorization: Bearer $WLROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4.1-mini",
    "messages": [
      { "role": "system", "content": "You are a precise API assistant. Keep answers concise and implementation-ready." },
      { "role": "user", "content": "Draft a short JSON schema for logging a chat completion request." }
    ],
    "temperature": 0.7,
    "max_tokens": 512,
    "stream": false
  }'