verboo code

Guide

Streaming with SSE

Receive deltas as they are generated and reduce perceived latency.

On this page

Enable stream

cURL
curl https://code.verboo.ai/router/v1/chat/completions \
  -H "Authorization: Bearer $VERBOO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<MODEL_ID>",
    "messages": [{"role": "user", "content": "Explain why low latency matters for developer tools."}],
    "stream": true
  }'

Stream protocol

SSE events
data: {"choices":[{"delta":{"content":"Olá"}}]}

data: {"choices":[{"delta":{},"finish_reason":"stop"}]}

data: {"choices":[],"usage":{"prompt_tokens":12,"completion_tokens":8,"total_tokens":20}}

data: [DONE]
  • Each event starts with data: and ends with a blank line.
  • Append choices[0].delta.content when present.
  • The final event may include usage before [DONE].

Cancellation and failures

Avoid duplicate responses

If the connection drops after content arrives, a retry creates a new generation. Decide whether your app discards, keeps the partial output, or asks for a continuation.

Propagate client cancellation, configure a connection timeout, and use a longer timeout for the complete stream.