OpenAI

gpt-5.4-pro

gpt-5.4-pro

View docs

Generate content through the unified API.

Pricing

/ 1M text units

Input: 5,294 – 10,588 Credits≈ $26.4708 – $52.9416
Official reference ~~$30.00 – $60.00~~11% below official
Output: 31,765 – 47,647 Credits≈ $158.8248 – $238.2372
Official reference ~~$180.00 – $270.00~~11% below official

Output

Chat

Added to catalog

Nov 1, 2026

Input

Examples

Message*

Estimate the cost first. Generation starts only after confirmation.

OutputFill example

{"arrival":"09:50"}

README

Generate content through the unified API.

Model capabilities

Input modalities: Text
Output modalities: Text
Context caching: Not supported
Tool calling: Not supported
Streaming: Supported
Batch inference: Not supported

API protocol support

Chat Completions: Supported
Responses: Not supported
Gemini: Not supported
Anthropic: Not supported

Parameters

Fields accepted in the request body for this model.

messagesmessages

Required

Advanced

max_tokensinteger

Optional

Range: ≥ 1

Pricing

Credits / 1M text units

Standard

Total input text units: [0, 272001)

Input: 5,294 Credits≈ $26.4708
Official reference ~~$30.00~~11% below official
Output: 31,765 Credits≈ $158.8248
Official reference ~~$180.00~~11% below official

Standard

Total input text units: [272001, 1000001)

Input: 10,588 Credits≈ $52.9416
Official reference ~~$60.00~~11% below official
Output: 47,647 Credits≈ $238.2372
Official reference ~~$270.00~~11% below official

Bill actual quantity · Rounding is applied once to the total cost

Official pricing source · Verified 2026-11-01

Prices are billed per unit consumed with no monthly minimum. See billing guide for Credits estimates and actual usage charges.

Code

View docs →

POST https://orux.top/api/v1/chat/completions

Code examples

Request body

curl 'https://orux.top/api/v1/chat/completions' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "messages": [
    {
      "role": "user",
      "content": "Railway case 530: a trip starts at 09:15 and lasts 35 minutes. Return only JSON {\"arrival\":\"HH:MM\"} with the arrival time."
    }
  ],
  "max_tokens": 1024,
  "model": "gpt-5.4-pro"
}'

Swipe horizontally to view the full content

Code examples

Response examples

{
  "id": "chatcmpl-...",
  "choices": [
    { "index": 0, "message": { "role": "assistant", "content": "Hello! How can I help you today?" } }
  ],
  "usage": { "prompt_tokens": 12, "completion_tokens": 9, "total_tokens": 21 }
}

Swipe horizontally to view the full content

Frequently asked questions

About gpt-5.4-pro pricing, capabilities and API access on Orux AI.

What is gpt-5.4-pro?

gpt-5.4-pro: Generate content through the unified API.

How much does gpt-5.4-pro cost on Orux AI?

See the pricing section on this page for gpt-5.4-pro pricing and applicable conditions. Charges depend on the selected parameters and recorded usage.

What inputs and outputs does gpt-5.4-pro support?

gpt-5.4-pro accepts Text and returns Text.

Does gpt-5.4-pro support tool calling and streaming?

gpt-5.4-pro on Orux AI — tool calling: Not supported; streaming: Supported.

Where can I access the gpt-5.4-pro API?

Create an Orux AI API key and send an authenticated POST request to https://orux.top/api/v1/chat/completions, using gpt-5.4-pro as the model identifier. Try the playground on this page and use the API example for the exact request format.