Hormouz AIHormouzSign in

OpenAI: GPT-5 Mini: AI model

GPT-5 Mini is an OpenAI model. A compact GPT-5 for lighter reasoning tasks at lower latency and cost, with up to 400K-token context. Reachable from inside Iran through Hormouz.

Context window:
400,000 tokens
Input:
$0.25/1M tokens
Output:
$2/1M tokens
Type:
text, image
  • Vision
  • Tools
  • Streaming
  • Long context
Good for:Popular for Marketing & SEO · #14Ranks are based on global usage data

Thinking levels: Always thinks · high · medium · low · minimal

GPT-5 Mini is a compact GPT-5 for lighter reasoning tasks at lower latency and cost. GPT-5 Mini keeps the same instruction-following and safety tuning as GPT-5 but runs faster and cheaper on lighter workloads. It supports a context window of up to 400K tokens, with training data through Sep 2024.

GPT-5 Mini is served through Hormouz behind an OpenAI-compatible API. It supports tool calling, image (vision) input and step-by-step reasoning. Point your base URL at Hormouz and drop in a Hormouz key, and existing OpenAI SDK code runs unchanged.

Pricing is usage-based: $0.25 per million input tokens and $2 per million output tokens. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

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-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorOpenAI
TypeText, Image
Context window400,000 tokens
Pricing$0.25/M in · $2.00/M out
APIChat Completions
CapabilitiesStreaming · Vision · Tools

Benchmarks

16.8
Intelligence Index
Better than 30% of models we compared
15.6
Coding Index
Better than 14% of models we compared
6.8
Agentic Index
Better than 32% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
82.8%
HLE
Humanity's Last Exam
21.5%
IFBench
Instruction-following
75.4%
AA-LCR
Long-context reasoning
72.3%
CritPt
Research-level physics reasoning
0%
AA Omniscience
Broad factual knowledge accuracy
25%
Non-Hallucination
Rate of avoiding fabricated answers
43.6%

Coding

SciCode
Python for scientific computing
39%
Terminal-Bench Hard
Agentic coding & terminal use
33.3%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
68.4%
GDPval
Economically valuable tasks
13.5%

Source: Artificial Analysis

Design Arena

How Design Arena works ↗
3D
Top 84%
1,048Elo
Win rate: 36.9%Avg time: 101s
ASCII Art
Top 71%
1,134Elo
Win rate: 44.7%Avg time: 39.7s
Code
Top 72%
1,121Elo
Win rate: 43.5%Avg time: 129s
Data Viz
Top 68%
1,139Elo
Win rate: 43.7%Avg time: 109s
Game Dev
Top 63%
1,142Elo
Win rate: 46.5%Avg time: 138s
SVG
Top 70%
1,090Elo
Win rate: 45.8%Avg time: 48.7s
UI Component
Top 69%
1,113Elo
Win rate: 41.9%Avg time: 111s
Website
Top 68%
1,132Elo
Win rate: 44.3%Avg time: 134s

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-mini",
    "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-mini",
    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-mini",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the OpenAI: GPT-5 Mini API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches OpenAI: GPT-5 Mini 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.
Create an accountBuy ChatGPT (OpenAI) API access, paid in rial

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does GPT-5 Mini cost?
Billing is usage-based: $0.25 per million input tokens and $2 per million output tokens. There is no fixed monthly fee. You pay only for what you use, and current rates are shown in the Hormouz dashboard.
How do I access GPT-5 Mini from inside Iran?
Create an account on Hormouz and generate an API key. Hormouz provides a stable path to GPT-5 Mini from inside Iran, with no foreign credit card or circumvention tooling required.
Is GPT-5 Mini compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing SDKs and chat-completions code run without a rewrite.
What context window and capabilities does GPT-5 Mini have?
GPT-5 Mini supports a context window of up to 400K tokens. It also supports tool calling, image (vision) input and step-by-step reasoning. That makes it a good fit for long documents, codebases and multi-turn conversations.
What is GPT-5 Mini good for?
GPT-5 Mini suits high-volume, latency-sensitive tasks: classification, extraction, routing, summarization and simple chat where cost per request matters.
What is GPT-5 Mini's knowledge cutoff?
GPT-5 Mini's training data runs through Sep 2024. For information newer than that, provide the relevant context in your prompt or connect a tool that fetches live data.

Updated 2026-10-13