Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.ai-stats.phaseo.app/llms.txt

Use this file to discover all available pages before exploring further.

All streaming endpoints use SSE-style frames: data: <json-or-sentinel>

​
Typical frame sequence

  1. One or more progress/delta frames.
  2. A completion frame with final status and usage.
  3. data: [DONE] sentinel.

​
JavaScript parser example

for await (const line of client.streamText({
  model: "openai/gpt-5-nano",
  messages: [{ role: "user", content: "Say hello." }],
  stream: true,
})) {
  if (!line.startsWith("data:")) continue;
  const payload = line.slice(5).trim();
  if (payload === "[DONE]") break;
  console.log(payload);
}

​
Python parser example

for line in client.stream_response({
    "model": "openai/gpt-5-nano",
    "input": "Say hello.",
    "stream": True,
}):
    if not line.startswith("data:"):
        continue
    payload = line[5:].strip()
    if payload == "[DONE]":
        break
    print(payload)

​
Endpoint format notes

  • /v1/chat/completions: chunked choices[].delta style events.
  • /v1/responses: responses-style output item/delta events.
  • /v1/messages: Anthropic-style events (message_start, content_block_delta, message_stop).
Last modified on February 18, 2026