OpenAI: o4 Mini (batch): AI model
- Context window:
- 200,000 tokens
- Input:
- $0.55/1M tokens
- Output:
- $2.2/1M tokens
- Type:
- text, image
- Vision
- Tools
- Streaming
- Long context
Thinking levels:
OpenAI: o4 Mini (batch) is a AI model from OpenAI, available through Hormouz via an OpenAI-compatible API with stable access from inside Iran.
OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...
Quickstart
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/o4-mini:batch",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | OpenAI |
|---|---|
| Type | Text, Image |
| Context window | 200,000 tokens |
| Pricing | $0.55/M in · $2.20/M out |
| API | Chat Completions |
| Capabilities | Streaming · Vision · Tools |
Benchmarks
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
78.4%
HLE
Humanity's Last Exam
16.5%
IFBench
Instruction-following
68.7%
AA-LCR
Long-context reasoning
61%
CritPt
Research-level physics reasoning
0.6%
AA Omniscience
Broad factual knowledge accuracy
24.8%
Non-Hallucination
Rate of avoiding fabricated answers
19.5%
Coding
Terminal-Bench Hard
Agentic coding & terminal use
15.2%
Agentic
τ²-Bench
Tool-use agents in dual-control scenarios
55.6%
Source: Artificial Analysis
Design Arena
How Design Arena works ↗3D
Top 99%864Elo
Win rate: 34%Avg time: 30.6s
Code
Top 92%982Elo
Win rate: 46.4%Avg time: 38.9s
Data Viz
Top 89%999Elo
Win rate: 50%Avg time: 29.2s
Game Dev
Top 86%1,016Elo
Win rate: 50%Avg time: 35.8s
UI Component
Top 89%990Elo
Win rate: 46.9%Avg time: 46.0s
Website
Top 90%992Elo
Win rate: 47.1%Avg time: 40.6s
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/o4-mini: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/o4-mini: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/o4-mini:batch",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the OpenAI: o4 Mini (batch) API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches OpenAI: o4 Mini (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