Streaming — OneHub

Set "stream": true to receive token-by-token chunks.

Docs

Docs Quick Start Authentication SDK Setup Available Models Rate Limits Chat Completions Streaming List Models Embeddings Image Generation Text to Speech Speech to Text Billing & Wallet Webhooks Errors

Streaming

With streaming enabled, responses arrive as SSE chunks in the OpenAI chat.completion.chunk format. The stream terminates with a final data: [DONE] line.

Chunk format

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1722500000,"model":"openai/gpt-5-nano","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1722500000,"model":"openai/gpt-5-nano","choices":[{"index":0,"delta":{"content":" world"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1722500000,"model":"openai/gpt-5-nano","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

curl

curl -N https://www.onehub.design/v1/chat/completions \
  -H "Authorization: Bearer sk-onehub-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5-nano",
    "messages": [{ "role": "user", "content": "Count from 1 to 3." }],
    "stream": true
  }'

Node.js

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://www.onehub.design/v1",
  apiKey: "sk-onehub-xxx",
});

const stream = await openai.chat.completions.create({
  model: "openai/gpt-5-nano",
  messages: [{ role: "user", content: "Count from 1 to 3." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

Notes

Chunks reference the same id, created, and model across the whole stream.
Usage is not included in the final chunk for streams. Check your dashboard's usage log for exact totals.