gpt-5.4-mini API

gpt-5.4-mini is the small member of the GPT-5.4 family: it keeps the family's reasoning ability and tool-use reliability while cutting per-token cost and latency, which makes it the default pick when you need GPT-5.4-class behavior across millions of requests rather than a handful of hard ones. Reasoning depth is adjustable per request — effort levels range from none (fast, near-instant replies) up to xhigh for problems that genuinely need deliberation — so one model can serve both a snappy chat frontend and a slower analytical backend. The specs are unusually generous for a mini-tier model: a 400,000-token context window, up to 128,000 output tokens per response, image input alongside text, and a knowledge cutoff of August 31, 2025. The large window means you can pass whole codebases, long transcripts, or multi-document bundles in a single call instead of building elaborate chunking pipelines; the 128K output ceiling covers long structured extractions and full-file code generation without truncation. On CaMeL Hub, gpt-5.4-mini is exposed through both the OpenAI Chat Completions API and the Responses API, with streaming and function calling fully supported. No code changes are needed beyond pointing your existing OpenAI SDK at https://api.camel-hub.com/v1 with a CaMeL Hub API key. Billing is per-token with separate input and output rates ($0.5625 and $3.375 per 1M tokens respectively), and the same key also reaches every other model on the platform, so you can route easy traffic to gpt-5.4-mini and escalate hard cases to a larger model behind one integration.

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-mini",
    "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-mini",
    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-mini",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);