Streaming

BVE Gateway supports streaming responses via Server-Sent Events (SSE) for /v1/chat/completions.

How streaming works

When "stream": true is set in the request body, the Fuelix response is piped directly to the client without buffering. BVE Gateway:

Does not call response.json() or response.text() on streaming responses
Does not buffer the response body
Preserves the upstream Content-Type (typically text/event-stream)
Preserves the upstream status code
Preserves SSE format exactly as Fuelix sends it

Only the X-BVE-Latency header is added; all other BVE-specific headers come from the safe header allowlist.

SSE format

Each streamed chunk is a data-only SSE event:

data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","created":1716288000,"model":"gpt-4o","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","created":1716288000,"model":"gpt-4o","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

cURL example

curl https://api.bve.me/v1/chat/completions \
  -H "Authorization: Bearer sk-bve-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{ "role": "user", "content": "Count from 1 to 5." }],
    "stream": true
  }'

OpenAI SDK streaming

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-bve-YOUR_KEY',
  baseURL: 'https://api.bve.me/v1',
});

const stream = await client.chat.completions.stream({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Count from 1 to 5.' }],
});

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

Safe headers on streaming responses

The same header allowlist applies to streaming responses:

Header	Forwarded
`content-type`	Yes
`cache-control`	Yes
`x-request-id`	Yes
`x-quota-allowed`	Yes
`x-quota-available`	Yes
`x-quota-reset`	Yes
`X-BVE-Latency`	Added by gateway
All others	Stripped