OpenAI: GPT-5.4 (batch): AI model
- Context window:
- 1,050,000 tokens
- Input:
- $1.25/1M tokens
- Output:
- $7.5/1M tokens
- Type:
- text, image
- Vision
- Tools
- Streaming
- Long context
Thinking levels: xhigh · high · medium · low · none
OpenAI: GPT-5.4 (batch) is a AI model from OpenAI, available through Hormouz via an OpenAI-compatible API with stable access from inside Iran.
GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...
Quickstart
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5.4:batch",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | OpenAI |
|---|---|
| Type | Text, Image |
| Context window | 1,050,000 tokens |
| Pricing | $1.25/M in · $7.50/M out |
| API | Chat Completions |
| Capabilities | Streaming · Vision · Tools |
Benchmarks
71.1
Coding Index
Better than 82% of models we compared
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
92%
HLE
Humanity's Last Exam
43.7%
IFBench
Instruction-following
73.9%
AA-LCR
Long-context reasoning
82%
CritPt
Research-level physics reasoning
23.4%
AA Omniscience
Broad factual knowledge accuracy
50.8%
Non-Hallucination
Rate of avoiding fabricated answers
8.3%
Coding
Terminal-Bench Hard
Agentic coding & terminal use
57.6%
Agentic
τ²-Bench
Tool-use agents in dual-control scenarios
87.1%
GDPval
Economically valuable tasks
37.4%
Source: Artificial Analysis
Design Arena
How Design Arena works ↗Ranking distribution
First
2,468
Second
3,253
Third
0
Fourth
0
5721 tournaments ?
3D
Top 64%1,112Elo
Win rate: 42.3%Avg time: 196s
ASCII Art
Top 29%1,210Elo
Win rate: 55.4%Avg time: 68.6s
Code
Top 34%1,216Elo
Win rate: 52.7%Avg time: 166s
Data Viz
Top 27%1,243Elo
Win rate: 56.6%Avg time: 157s
Game Dev
Top 24%1,251Elo
Win rate: 57.6%Avg time: 203s
SVG
Top 28%1,194Elo
Win rate: 57.8%Avg time: 65.0s
UI Component
Top 28%1,247Elo
Win rate: 57.4%Avg time: 117s
Website
Top 35%1,222Elo
Win rate: 52.7%Avg time: 158s
Android Native
Top 97%1,046Elo
Win rate: 47.4%
Full-Stack
Top 91%1,016Elo
Win rate: 40.9%
Godot Game Dev
Top 69%1,135Elo
Win rate: 46.9%
Mobile Apps
Top 93%1,084Elo
Win rate: 46.1%
Web Apps
Top 90%1,052Elo
Win rate: 40.3%
Metrics sourced from Design Arena
Code example
cURL
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5.4:batch",
"messages": [{"role": "user", "content": "Hello!"}]
}'Python
from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
model="openai/gpt-5.4:batch",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)JavaScript
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
model: "openai/gpt-5.4:batch",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the OpenAI: GPT-5.4 (batch) API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches OpenAI: GPT-5.4 (batch) and 600+ other models, and you pay only for what you use.
- No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessUpdated 2026-10-13