OpenAIText APIOnline

codex-gpt-5.4-mini

GPT-5.4 mini is an efficient reasoning model for coding, tool use, and high-throughput agent workflows, with a 400K-token context window, image input, and configurable reasoning effort.

API access

Endpoint

POST /v1/responses

Base URL

https://apidev.hiapi.ai

Uses the OpenAI Responses format. One HiAPI key works across all available models.

Input price

1,500 Credits

/ 1M tokens

Output price

9,000 Credits

/ 1M tokens

Context

400K

context window

Max output

128K

output tokens

Try codex-gpt-5.4-mini

Ask a question, upload images, or paste from clipboard. Then inspect the streamed answer, token usage, latency, and estimated cost.

Upload or paste up to 4 images, 10 MB each. Images are safety reviewed.

codex-gpt-5.4-mini API Quickstart

Call codex-gpt-5.4-mini with the streaming OpenAI Responses format. Copy a ready-to-use cURL, Python, or Node.js example below.

Code Example

API Endpoint:/v1/responses

curl -N -X POST "https://apidev.hiapi.ai/v1/responses" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "codex-gpt-5.4-mini",
  "input": [
    {
      "type": "message",
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "检查当前仓库，找出一个可以安全改进的问题，并说明修改理由。"
        }
      ]
    }
  ],
  "stream": true,
  "store": false,
  "reasoning": {
    "effort": "medium"
  }
}'

Tip: Replace YOUR_API_KEY with your actual API key from the API Keys page.

Uses the OpenAI Responses format. Keep stream: true, send input as a message array, and set reasoning effort with reasoning.effort.

Image understanding example

Combine input_text and input_image in one input message. Use a public HTTPS image URL; Playground uploads automatically provide a temporary reviewed URL.

API Endpoint:/v1/responses

curl -N -X POST "https://apidev.hiapi.ai/v1/responses" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "codex-gpt-5.4-mini",
  "input": [
    {
      "type": "message",
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Describe the main subject, setting, and important visual details."
        },
        {
          "type": "input_image",
          "image_url": "https://static.hiapi.ai/example/subject-1.jpg",
          "detail": "low"
        }
      ]
    }
  ],
  "stream": true,
  "store": false,
  "reasoning": {
    "effort": "medium"
  }
}'

Tip: Replace YOUR_API_KEY with your actual API key from the API Keys page.

Uses the OpenAI Responses format. Keep stream: true, send input as a message array, and set reasoning effort with reasoning.effort.

Responses API

Request fields at a glance

Start with core fields, then enable advanced capabilities as needed.

3 required4 capability fields

Core fields

The fields that form a valid request

model: Use the model ID shown on this page.
input: Pass the current conversation context as a message array.
stream: Must be set to true.
store: Fixed to false and shown explicitly in examples.

Capability fields

Enable reasoning, context, and tools as needed

reasoning.effort: none, low, medium, high, xhigh, or max; defaults to medium.
instructions: Define the role and response requirements.
previous_response_id: Use with compatible storage and response chaining; with store=false, replay context from the client.
tools / tool_choice: Declare and control function tool calls.

Max output is a model specification limit, not a per-request generation target. Examples show only the runtime fields currently available and verified on HiAPI.

Manage API keysUse the same HiAPI key across all available models.

codex-gpt-5.4-mini API Pricing

Billing is based on actual input, output, and cached token usage. All prices below are shown per 1 million tokens.

Input tokens: 1,500 Credits/ 1M tokens
Output tokens: 9,000 Credits/ 1M tokens

Cache read: 150 Credits/ 1M tokens
Cache write: -

codex-gpt-5.4-mini Model Specifications

These specifications reflect the current public HiAPI text request contract. Undisclosed capabilities are not inferred by the page.

Streaming: Supported
Tool calling: Supported
Structured JSON: Supported
Reasoning: Supported
Input modalities: text · image
Output modalities: text
Reasoning efforts: none · low · medium · high · xhigh
Max output: 128K

About codex-gpt-5.4-mini

GPT-5.4 mini is an efficient reasoning model for coding, tool use, and high-throughput agent workflows, with a 400K-token context window, image input, and configurable reasoning effort.

HiAPI exposes this model through /v1/responses. Test prompts and parameters in the Playground, then use the same HiAPI API key in your server application.

Provider: OpenAI
Endpoint: /v1/responses
Context window: 400K
Released: Not disclosed

How to Use codex-gpt-5.4-mini

The Playground and API share the same model ID, so three steps take a tested prompt into production.

Step 1
Validate online
Test instructions, input, and reasoning.effort in the Playground.
Step 2
Manage API keys
View an existing key or create another after signing in; one key works across all available models.
Step 3
Integrate your server
Send requests to /v1/responses and track cost with the usage object.

Frequently asked questions

What is the codex-gpt-5.4-mini API?

The codex-gpt-5.4-mini API is a text generation endpoint available through one HiAPI API key.

How is the codex-gpt-5.4-mini API priced?

codex-gpt-5.4-mini API uses usage-based pricing. This page includes pricing, parameters, examples, and integration code.

How do I call the codex-gpt-5.4-mini API?

Send a POST request to /v1/responses with the model name, input, and one API key. This page includes cURL, Python, and Node.js examples.