gpt-5.4 API

gpt-5.4 is the mainline model of OpenAI's GPT-5.4 family, sitting between the budget-oriented gpt-5.4-mini and the heavyweight gpt-5.4-pro. It accepts both text and images and is documented with a 1,050,000-token context window and up to 128,000 output tokens — one of the largest working windows available today. That scale changes what a single request can do: an entire mid-sized codebase, a full contract bundle, or hours of meeting transcripts fit into one prompt without chunking pipelines or retrieval scaffolding. On CaMeL Hub, gpt-5.4 is served through the standard OpenAI-compatible surface: the /v1/chat/completions endpoint and the newer /v1/responses endpoint both work, with streaming, vision (image input), and function calling supported. Existing code built on the official OpenAI SDK runs unchanged — swap the base_url to https://api.camel-hub.com/v1, use your CaMeL Hub API key, and keep the same request format, tool schemas, and streaming handlers. Cost-wise, gpt-5.4 is a mid-tier flagship: at $1.875 per 1M input and $11.25 per 1M output tokens, the 6x input/output spread means input-heavy workloads (long-document Q&A, large-context code review) are markedly cheaper per request than generation-heavy ones. If your task is mostly bulk classification or short answers over short prompts, gpt-5.4-mini is the more economical pick; reach for gpt-5.4 when you need the full context window, stronger multi-step reasoning over tools, or reliable behavior on long agentic sessions. Billing on CaMeL Hub is strictly per-token pay-as-you-go, funded by one-time top-ups or subscription plans.

curl https://api.camel-hub.com/v1/chat/completions \
  -H "Authorization: Bearer $CAMEL_HUB_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="$CAMEL_HUB_KEY",
    base_url="https://api.camel-hub.com/v1",  # <-- the only change vs. the OpenAI default
)

resp = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CAMEL_HUB_KEY,
  baseURL: "https://api.camel-hub.com/v1", // <-- the only change vs. the OpenAI default
});

const resp = await client.chat.completions.create({
  model: "gpt-5.4",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);