OpenAI: gpt-oss-120b (batch): AI model
- Context window:
- 131,072 tokens
- Input:
- $0.03/1M tokens
- Output:
- $0.14/1M tokens
- Type:
- text
- Tools
- Streaming
- Long context
Thinking levels: Always thinks · high · medium · low
OpenAI: gpt-oss-120b (batch) is a AI model from OpenAI, available through Hormouz via an OpenAI-compatible API with stable access from inside Iran.
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
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-oss-120b:batch",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | OpenAI |
|---|---|
| Type | Text |
| Context window | 131,072 tokens |
| Pricing | $0.03/M in · $0.14/M out |
| API | Chat Completions |
| Capabilities | Streaming · Tools |
Benchmarks
11.6
Intelligence Index
Better than 19% of models we compared
30.4
Coding Index
Better than 33% of models we compared
3.7
Agentic Index
Better than 29% of models we compared
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
78.2%
HLE
Humanity's Last Exam
19.6%
IFBench
Instruction-following
69%
AA-LCR
Long-context reasoning
52%
CritPt
Research-level physics reasoning
1.1%
AA Omniscience
Broad factual knowledge accuracy
21.8%
Non-Hallucination
Rate of avoiding fabricated answers
9.2%
Coding
SciCode
Python for scientific computing
34%
Terminal-Bench Hard
Agentic coding & terminal use
23.5%
Agentic
τ²-Bench
Tool-use agents in dual-control scenarios
65.8%
GDPval
Economically valuable tasks
5.6%
Source: Artificial Analysis
Design Arena
How Design Arena works ↗3D
Top 96%912Elo
Win rate: 29.4%Avg time: 16.9s
Code
Top 95%969Elo
Win rate: 33.4%Avg time: 24.1s
Data Viz
Top 90%995Elo
Win rate: 43.6%Avg time: 12.6s
Game Dev
Top 88%1,005Elo
Win rate: 40.5%Avg time: 23.3s
UI Component
Top 94%934Elo
Win rate: 35.7%Avg time: 16.2s
Website
Top 92%974Elo
Win rate: 32.5%Avg time: 25.4s
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-oss-120b: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-oss-120b: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-oss-120b:batch",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the OpenAI: gpt-oss-120b (batch) API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches OpenAI: gpt-oss-120b (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