BifrostAPI
Models/OpenAI/gpt-5.4
OpenAI

GPT-5.4

TextVisionReasoning
Context
1.1M
Input
$2.5
/M tokens
Output
$15
/M tokens

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.

Quick start

How to call

POST /v1/chat/completions
bash
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","messages":[{"role":"user","content":"Hello!"}]}'

→ OpenAI-compatible. Add "stream": true (+ "stream_options":{"include_usage":true}) for SSE.

Reasoning effort: gpt-5.4-low / -medium / -high / -xhigh / -max, or the param reasoning_effort.

Auth, billing & streaming → Quickstart

Reasoning effort supported

Append -low / -medium / -high / -xhigh to the model name and the gateway sets the reasoning_effort parameter automatically.

More from OpenAI