OpenAI: GPT-4.1 (batch): AI model
- Context window:
- 1,047,576 tokens
- Input:
- $1/1M tokens
- Output:
- $4/1M tokens
- Type:
- text, image
- Vision
- Tools
- Streaming
- Long context
OpenAI: GPT-4.1 (batch) is a AI model from OpenAI, available through Hormouz via an OpenAI-compatible API with stable access from inside Iran.
GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...
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-4.1:batch",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | OpenAI |
|---|---|
| Type | Text, Image |
| Context window | 1,047,576 tokens |
| Pricing | $1.00/M in · $4.00/M out |
| API | Chat Completions |
| Capabilities | Streaming · Vision · Tools |
Benchmarks
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
66.6%
HLE
Humanity's Last Exam
4.2%
IFBench
Instruction-following
43%
AA-LCR
Long-context reasoning
68.3%
CritPt
Research-level physics reasoning
0%
AA Omniscience
Broad factual knowledge accuracy
27.8%
Non-Hallucination
Rate of avoiding fabricated answers
6.7%
Coding
Terminal-Bench Hard
Agentic coding & terminal use
13.6%
Agentic
τ²-Bench
Tool-use agents in dual-control scenarios
47.1%
Source: Artificial Analysis
Design Arena
How Design Arena works ↗3D
Top 99%860Elo
Win rate: 30.9%Avg time: 67.8s
Code
Top 86%1,031Elo
Win rate: 50.9%Avg time: 72.7s
Data Viz
Top 74%1,111Elo
Win rate: 59.5%Avg time: 60.3s
Game Dev
Top 74%1,092Elo
Win rate: 59.1%Avg time: 97.2s
UI Component
Top 88%1,007Elo
Win rate: 49.7%Avg time: 65.6s
Website
Top 84%1,045Elo
Win rate: 52.3%Avg time: 71.5s
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-4.1: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-4.1: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-4.1:batch",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the OpenAI: GPT-4.1 (batch) API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches OpenAI: GPT-4.1 (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