LLM API

gpt-5.4 · API guide

Integrate gpt-5.4 through openai. Request examples, parameters, authentication and result handling.

POST/v1/chat/completionsMODELgpt-5.4

Official reference gpt-5.4Checked 2026-10-14Official docs

Code examples & responses

Request & responseExamples

POST/v1/chat/completions

Server-side request

curl "https://newrouters.com/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  --data '{
  "model": "gpt-5.4",
  "messages": [
    {
      "role": "user",
      "content": "Explain how an HTTP request works in three concise steps."
    }
  ],
  "max_completion_tokens": 1024,
  "stream": false
}'

Server-side request

const apiBaseUrl = "https://newrouters.com";
const apiKey = process.env.API_KEY;
if (!apiKey) throw new Error("Set API_KEY in your server environment");

const response = await fetch(apiBaseUrl + "/v1/chat/completions", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "Bearer " + apiKey
  },
  body: JSON.stringify({
  "model": "gpt-5.4",
  "messages": [
    {
      "role": "user",
      "content": "Explain how an HTTP request works in three concise steps."
    }
  ],
  "max_completion_tokens": 1024,
  "stream": false
})
});

const result = await response.json();
if (!response.ok) throw new Error(JSON.stringify(result));
console.log(result);

Server-side request

import json
import os
from urllib.request import Request, urlopen

api_base_url = "https://newrouters.com"
api_key = os.environ["API_KEY"]
body = json.loads("{\"model\":\"gpt-5.4\",\"messages\":[{\"role\":\"user\",\"content\":\"Explain how an HTTP request works in three concise steps.\"}],\"max_completion_tokens\":1024,\"stream\":false}")

request = Request(
    api_base_url + "/v1/chat/completions",
    data=json.dumps(body).encode("utf-8"),
    headers={
    "Content-Type": "application/json",
    "Authorization": "Bearer " + api_key
    },
    method="POST",
)
with urlopen(request) as response:
    print(json.load(response))

The API origin is filled in. Set API_KEY before running. Examples never submit automatically.

ResponseSelected fields · illustrative values

200Successful result

JSON

{
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "..."
      },
      "finish_reason": "stop"
    }
  ]
}

Integration flowOpenAI · Native protocol

Prepare a request01
API key + model ID
Use the model’s native protocol and authentication.
SDK / HTTP
Call the native API02
POST /v1/chat/completions
Submit the request structure documented on this page.
OpenAI
Read the response03
choices[].message
JSON returns a complete result; read SSE increments using native event formats.
JSON / SSE

Use the exact API model ID gpt-5.4. This guide describes the platform contract; check the live catalog before calling the model.

Availability

An active catalog record means the model is configured; it does not guarantee an available channel. Before integration, check lifecycle, health.status and contract in GET /v1/public-model-catalog. Account pricing is shown in the dashboard. If supply is unavailable, wait for recovery or explicitly select another model. Do not repeatedly submit requests with an unknown outcome.

Request example

The platform origin is filled in at build time. Set API_KEY to your server-side key before running.

curl "https://newrouters.com/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  --data '{
  "model": "gpt-5.4",
  "messages": [
    {
      "role": "user",
      "content": "Explain how an HTTP request works in three concise steps."
    }
  ],
  "max_completion_tokens": 1024,
  "stream": false
}'

Protocol and response

This model uses the openai protocol. Read its native response and usage fields; do not wrap the request in the media task input envelope.

Supported endpoint templates：

POST /v1/chat/completions
POST /v1/responses

Limit	Catalog value
Context tokens	1050000
Maximum output tokens	128000

For streaming, use the native protocol streaming option and parse its events; check supported capabilities in the live catalog.

Official sources and identity

Checked: 2026-10-14 · Platform model: gpt-5.4 · Official reference: gpt-5.4

Pricing and troubleshooting

Check current availability, contract and account pricing before integration. Keep request IDs and usage receipts when diagnosing errors. Complete API reference