Seedance 2.5 is live — 30-second cinematic video with native audio & real-person references

GPT-5.4 API — OpenAI-Compatible, Production-Ready

GPT-5.4 is OpenAI's established reasoning model — 1M context, 128K max output, and a drop-in /v1/chat/completions endpoint. The cost-efficient route in the GPT family for production traffic that doesn't need GPT-5.5's newest reasoning gains.

Highlights
OpenAI GPT-5 line · streaming chat
Best for
General assistants, content, coding
Input
Chat messages (OpenAI-compatible)
Output
Text, streaming optional
GPT-5.4modelgpt-5.4

GPT-5.4 playground

Chat models run on the api.reapi.ai gateway, which has its own console and its own key. Open the console to run GPT-5.4 through the OpenAI-compatible Chat Completions surface.

Open consoleToken rates

What is the GPT-5.4 API?

GPT-5.4 is OpenAI's established reasoning model, served on reAPI as a drop-in OpenAI-compatible /v1/chat/completions endpoint. It reads a 1M-token context window, returns up to 128K tokens in a single response, and covers function calling, JSON-mode output and low-latency streaming — the cost-efficient route in the GPT family for production traffic that does not need GPT-5.5's newest reasoning gains. Billing is per 1M tokens, with input and output priced separately.

What you can build with this model

Real-world workflows and production use cases you can build and ship with this model.

GPT-5.4 powering a production chatbot at scale

High-volume production chat traffic

Run GPT-5.4 as the default model behind a chatbot, support assistant, or internal copilot. The cost-efficient pricing in the GPT family keeps per-request spend low while you still get reasoning, streaming, and tool use behind one endpoint.

Read the API docs
GPT-5.4 summarising a long document in one request

Long-context summarisation and review

Feed entire policy documents, transcripts, contracts, or research sets into a single GPT-5.4 call. The 1M token context window means you rarely need to chunk — the model sees the whole document and returns a coherent summary, review, or comparison.

GPT-5.4 extracting structured JSON from free text

Structured extraction and classification

Pull structured JSON out of free-text inputs, classify tickets and reviews into a fixed taxonomy, or normalise messy fields against a schema. GPT-5.4 returns reliable JSON via `response_format` and standard OpenAI tool calling — no custom parser required.

Pricing

Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.

First test cost
$11,000 credits

One sample at the cheapest tier (1M tokens).

Testing budget guide
Add credits
$10
≈ 10 tests
$50
≈ 50 tests
$100
≈ 100 tests
ModelCategoryPrice
TokensInput tokens
$1
1M tokens
Output tokens
$6
1M tokens

Why reAPI

drop-in migration path

The GPT-5.4 API speaks OpenAI Chat Completions verbatim. Moving an existing OpenAI integration is a base URL, an API key, and a model-string change — not a platform rewrite. Same `messages` array, same `stream` / `temperature` / `top_p` / `frequency_penalty` / `presence_penalty` parameters, same SSE wire format.

Cost-efficient production route

GPT-5.4 is the lowest-priced route in the GPT family — pay-as-you-go in USD, no monthly minimum. Pick it for established workloads where the volume is high and the marginal cost of each call matters more than squeezing the last few points of reasoning quality.

One key across GPT, Claude, and Gemini

A single api.reapi.ai key unlocks GPT-5.4 alongside GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and every other frontier chat model on the platform. Compare vendors, add fallbacks, and route traffic per call with a configuration change instead of an integration project.

Ship the GPT-5.4 API in three steps

  1. step 01

    Create an account and key on api.reapi.ai

    Sign up at api.reapi.ai, open the console, generate an API key under API Keys, and top up tokens under Top Up. The chat workspace is separate from the reapi.ai image/video gateway — keys do not cross over.

    Open
  2. step 02

    Send your first request

    POST https://api.reapi.ai/v1/chat/completions with `model: "gpt-5.4"`, your `messages` array, and any optional parameters. The endpoint uses the standard chat-completions format, including streamed responses.

    Open
  3. step 03

    Read the API docs

    Open the GPT-5.4 docs for the full request schema, error envelope, and language-specific code samples (cURL, Python, Node.js, Go).

    Open
docs/api/gpt-5-4

API reference

Drop-in code and the full parameter table.

View full reference
curl https://api.reapi.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "group": "default",
    "messages": [
      { "role": "user", "content": "Hello" }
    ],
    "stream": true,
    "temperature": 0.7,
    "top_p": 1,
    "frequency_penalty": 0,
    "presence_penalty": 0
  }'

Parameter validation failed

Rejected synchronously with the failing field named. Check enum values, ranges, and URL fields — nothing is charged.

Authentication or balance issue

401 means a missing or invalid Bearer key; 402 means the reserve exceeds your balance. Manage keys and credits in the console.

Content or material rejected

Reference material and outputs pass automated moderation. Rejected tasks fail with a clear error and a full refund.

Task failed or timed out

A task that reaches a failed state is never charged — the reserve refunds automatically. Keep the task id and retry when ready.

Frequently asked questions

Common questions about this model.

GPT-5.4 is billed pay-as-you-go in USD against your api.reapi.ai token balance — see the pricing card on this page for the live per-1M-token rate. Failed requests are not charged.

Related models

Explore more models in the same category.

View all models
start building

Ready to ship?

Try it in the playground or grab an API key to integrate now.

Get API keyView API docs