GPT gpt-5.4-pro API
A model variant exposed through RunAPI's unified AI API.
Operational
·
text
·
Commercial use supported
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/gpt -g
Or paste this prompt to your AI agent:
Install the GPT skill for me: 1. Clone https://github.com/runapi-ai/gpt 2. Copy the skills/gpt/ directory into your user-level skills directory (e.g. ~/.claude/skills/ for Claude Code, ~/.codex/skills/ for Codex). 3. Verify that SKILL.md is present. 4. Confirm the install path when done.
Switch variant
APERÇU
GPT gpt-5.4-pro is available through the same RunAPI auth, SDKs, and agent skill workflow.
- Unified endpoint
- SDK snippets
- Agent install path
- Les générations échouées ne sont pas facturées
TARIFS
TARIFS
Les générations échouées ne sont pas facturées
Responses API
Input
$15.00
/ 1M tokens
Output
$90.00
/ 1M tokens
FICHE TECHNIQUE
FICHE TECHNIQUE
| Model ID | gpt-5.4-pro |
| Fournisseur | OpenAI |
| Modalité | text |
| Task type | synchronous |
| Facturation | 1K tokens |
| Endpoint | /v1/responses |
| Commercial | Yes |
| Status | Operational |
DÉMARRAGE RAPIDE
Quickstart — gpt-5.4-pro
curl -X POST https://runapi.ai/v1/responses \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.4-pro",
"messages": [
{
"role": "user",
"content": "Analyze this quarterly revenue data and produce a summary with key trends, anomalies, and three recommendations."
}
]
}'
import { GptClient } from "@runapi.ai/gpt";
const client = new GptClient();
const result = await client.response.run({
model: "gpt-5.4-pro",
messages: [{"role":"user","content":"Analyze this quarterly revenue data and produce a summary with key trends, anomalies, and three recommendations."}],
});
require "runapi/gpt"
client = RunApi::Gpt::Client.new
result = client.response.run(
model: "gpt-5.4-pro",
messages: [{role: "user", content: "Analyze this quarterly revenue data and produce a summary with key trends, anomalies, and three recommendations."}]
)
FONCTIONNEMENT
How to use gpt-5.4-pro
01
Choose endpoint
Pick the endpoint and copy the SDK snippet.
02
Pass model ID
Use this variant ID in the request body.
03
Run task
Submit the request and store the returned task ID.
04
Collect output
Poll or receive the callback when the task finishes.
DIFFÉRENCES
How gpt-5.4-pro compares
VS CODEX-AUTO-REVIEW
gpt-5.4-pro
codex-auto-review
VS GPT-5.2
gpt-5.4-pro
Professional knowledge work; Thinking mode for deep tasks
VS GPT-5.2-PRO
gpt-5.4-pro
gpt-5.2-pro
CAS D’USAGE
Where to use this variant
Chat
Use LLMs for chat and reasoning.
Code
Generate and review implementation work.
Automation
Connect models into backend tasks.
FAQ
Frequently asked questions about gpt-5.4-pro
How do I select gpt-5.4-pro?
Pass the model ID shown in the quickstart.
Is pricing usage-based?
Yes. Pricing is metered per call or unit.
Other GPT variants
gpt-5.4-nano
Cheapest
5.4-nano
$0.030 / 1K tokens
gpt-5.3-codex-spark
5.3-codex-spark
$0.050 / 1K tokens
gpt-5.4-mini
5.4-mini
$0.050 / 1K tokens
codex-auto-review
codex-auto-review
$0.130 / 1K tokens
gpt-5.2
5.2
$0.130 / 1K tokens
gpt-5.3-codex
5.3-codex
$0.130 / 1K tokens
gpt-5.4
5.4
$0.130 / 1K tokens
gpt-5.5
5.5
$0.250 / 1K tokens
gpt-5.2-pro
Quality
5.2-pro
$1.00 / 1K tokens
gpt-5.5-pro
Quality
5.5-pro
$1.25 / 1K tokens
Related models
COMMENCER