Endpoint
openai SDK by changing baseURL.
Request body
Streaming
Setstream: true to get token-by-token SSE chunks (OpenAI format with
data: {…}\n\n events ending in data: [DONE]).
Billing
1 credit per 10,000 tokens (input + output, minimum 1 per call). For streamed responses, the final chunk includes theusage block we use to
compute the bill.