Text model API

GPT-5.4 Mini API

openai/gpt-5.4-mini is OpenAI’s strongest mini model in the GPT-5.4 family, built for fast, cost-efficient coding, tool use, multimodal reasoning, and agent-style workflows. It brings many of the strengths of GPT-5.4 into a smaller, lower-latency model that works especially well for high-volume production tasks, coding assistants, subagents, and computer-use scenarios.

Model id
gpt-54-mini
Takes
Text (required)
Makes
Text
Endpoint
POST /api/v1/chat/completions
Made by
OpenAI
Mode
Synchronous

Call GPT-5.4 Mini

Base URL https://payload.rentprompts.com/api/v1. Replace the placeholder with your key.

Model gpt-54-mini

POST /api/v1/chat/completions

curl https://payload.rentprompts.com/api/v1/chat/completions \
  -H "Authorization: Bearer rp_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gpt-54-mini",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about APIs."
    }
  ],
  "max_tokens": 256
}'

Replace rp_live_YOUR_KEY with your key, ideally via the RENTPROMPTS_API_KEY environment variable. Keys are shown only once, so they are never filled in here. Get your API key →

What a typical call costs

Worked out from GPT-5.4 Mini's published price (0.68 J in · 1.9 J out / 1K tokens). You pay only for successful results, from your Joule balance.
  • 1,000 input + 500 output tokens1.63 Joules
  • 10,000 input + 2,000 output tokens10.6 Joules

Send requests to POST /api/v1/chat/completions. GPT-5.4 Mini answers synchronously: the result comes back in the response to the same request. Token counts come from the model's own usage report, so a real call may use more or fewer tokens than this example.

Settings

Optional parameters this model accepts (pass them in settings on /v1/run, or as top-level fields where OpenAI defines them).

This model has no extra settings. Send the standard fields shown in the example.

GPT-5.4 Mini API — Pricing & Code Examples | RentPrompts