OpenAI: GPT-5.2 (batch): AI model
- Context window:
- 400,000 tokens
- Input:
- $0.88/1M tokens
- Output:
- $7/1M tokens
- Type:
- text, image
- Vision
- Tools
- Streaming
- Long context
Thinking levels: xhigh · high · medium · low · none
OpenAI: GPT-5.2 (batch) is a AI model from OpenAI, available through Hormouz via an OpenAI-compatible API with stable access from inside Iran.
GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...
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-5.2:batch",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | OpenAI |
|---|---|
| Type | Text, Image |
| Context window | 400,000 tokens |
| Pricing | $0.88/M in · $7.00/M out |
| API | Chat Completions |
| Capabilities | Streaming · Vision · Tools |
Benchmarks
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
90.3%
HLE
Humanity's Last Exam
37.7%
IFBench
Instruction-following
75.4%
AA-LCR
Long-context reasoning
82.7%
CritPt
Research-level physics reasoning
11.6%
AA Omniscience
Broad factual knowledge accuracy
44.3%
Non-Hallucination
Rate of avoiding fabricated answers
18.8%
Coding
Terminal-Bench Hard
Agentic coding & terminal use
47%
Agentic
τ²-Bench
Tool-use agents in dual-control scenarios
84.8%
Source: Artificial Analysis
Design Arena
How Design Arena works ↗Ranking distribution
First
3,201
Second
3,439
Third
0
Fourth
0
6640 tournaments ?
Website
Top 42%1,201Elo
Win rate: 54.4%Avg time: 239s
Android Native
Top 86%1,074Elo
Win rate: 49.1%
Full-Stack
Top 86%1,041Elo
Win rate: 44.3%
Godot Game Dev
Top 67%1,142Elo
Win rate: 48.1%
Mobile Apps
Top 83%1,091Elo
Win rate: 46.8%
Web Apps
Top 86%1,079Elo
Win rate: 45.5%
3D
Top 79%1,064Elo
Win rate: 45.3%Avg time: 120s
Code
Top 61%1,156Elo
Win rate: 50.5%Avg time: 152s
Data Viz
Top 39%1,209Elo
Win rate: 56.1%Avg time: 162s
Game Dev
Top 38%1,199Elo
Win rate: 56.7%Avg time: 169s
UI Component
Top 45%1,188Elo
Win rate: 54%Avg time: 155s
ASCII Art
Top 50%1,163Elo
Win rate: 50.7%Avg time: 45.8s
SVG
Top 53%1,135Elo
Win rate: 53.1%Avg time: 40.5s
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-5.2: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-5.2: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-5.2:batch",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the OpenAI: GPT-5.2 (batch) API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches OpenAI: GPT-5.2 (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