GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.
curl https://conduit-api.bifrostapi.net/v1/chat/completions \
-H "Authorization: Bearer ck-YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-5.4-mini","messages":[{"role":"user","content":"Hello!"}]}'→ OpenAI-compatible. Add "stream": true (+ "stream_options":{"include_usage":true}) for SSE.
Reasoning effort: gpt-5.4-mini-low / -medium / -high / -xhigh / -max, or the param reasoning_effort.
Reasoning effort supported
Append -low / -medium / -high / -xhigh to the model name and the gateway sets the reasoning_effort parameter automatically.