Skip to content
GPT-6.1 Sol & Luna, Claude Opus 5.5, Sonnet 5.5, Haiku 5.5, and Gemini 4 Argon are now available

Guides

Streaming

Receive tokens incrementally over SSE.

Add "stream": true to the request body. The response is a Server-Sent Events stream of data: {...} lines, terminated by data: [DONE].

terminal.sh
curl -N https://api.sobatnetwork.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $SOBAT_API_KEY" \
-d '{"model":"sobat/gpt-6-sol","stream":true,"messages":[{"role":"user","content":"Hi"}]}'

With the OpenAI SDK, simply pass stream: true and iterate over the incoming chunks.