All models / gpt-realtime-2.1 / Microsoft

gpt-realtime-2.1

model id: openai/gpt-realtime-2.1/microsoft

Audio in → Audio out

Price

$32 / 1M audio input tokens

per 1M tokens, by modality — billed by the session's real usage across every response.done event, not a flat per-minute or per-call rate

Token type	Input	Cached input	Output
Text	$4	$0.4	$24
Audio	$32	$0.4	$64
Image	$5	$0.5	$0

+ VideoRouter platform fee: 2% of provider cost — billed as its own line, never blended into the rates above.

import asyncio, json, websockets

async def main():
    async with websockets.connect(
        "wss://videorouter.sh/v1/realtime?model=azure/gpt-realtime-2.1",
        additional_headers={"Authorization": "Bearer llmr_sk_..."},
    ) as ws:
        print(json.loads(await ws.recv()))  # -> {"type": "session.created", ...}

        await ws.send(json.dumps({"type": "session.update",
                              "session": {"type": "realtime", "instructions": "You are a helpful assistant."}}))

        # ... input_audio_buffer.append chunks, then response.create ...
        await ws.send(json.dumps({"type": "response.create"}))
        print(json.loads(await ws.recv()))  # -> response.* stream, ending in response.done + usage

asyncio.run(main())

const ws = new WebSocket("wss://videorouter.sh/v1/realtime?model=azure/gpt-realtime-2.1", {
  headers: { Authorization: "Bearer llmr_sk_..." },
});

ws.onopen = () => {
  ws.send(JSON.stringify({ type: "session.update", session: { type: "realtime", instructions: "You are a helpful assistant." } }));
};

ws.onmessage = (event) => {
  const msg = JSON.parse(event.data);
  if (msg.type === "session.created") ws.send(JSON.stringify({ type: "response.create" }));
  if (msg.type === "response.done") console.log(msg.response.usage);
};

gpt-realtime-2.1

Customer reviews