Hormouz AIHormouzSign in

Anthropic: Claude Opus 4.5 (batch): AI model

Context window:
200,000 tokens
Input:
$2.5/1M tokens
Output:
$12.5/1M tokens
Type:
text, image
  • Vision
  • Tools
  • Streaming
  • Long context

Thinking levels:

Anthropic: Claude Opus 4.5 (batch) is a AI model from Anthropic, available through Hormouz via an OpenAI-compatible API with stable access from inside Iran.

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-4.5:batch",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorAnthropic
TypeText, Image
Context window200,000 tokens
Pricing$2.50/M in · $12.50/M out
APIChat Completions
CapabilitiesStreaming · Vision · Tools

Benchmarks

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
81%
HLE
Humanity's Last Exam
13.2%
IFBench
Instruction-following
43%
AA-LCR
Long-context reasoning
70.7%
CritPt
Research-level physics reasoning
0.3%
AA Omniscience
Broad factual knowledge accuracy
40.9%
Non-Hallucination
Rate of avoiding fabricated answers
23.8%

Coding

Terminal-Bench Hard
Agentic coding & terminal use
40.9%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
86.3%

Source: Artificial Analysis

Design Arena

How Design Arena works ↗
3D
Top 29%
1,224Elo
Win rate: 58.5%Avg time: 86.1s
ASCII Art
Top 34%
1,201Elo
Win rate: 54.8%Avg time: 48.3s
Code
Top 26%
1,248Elo
Win rate: 59.5%Avg time: 124s
Data Viz
Top 23%
1,251Elo
Win rate: 58.5%Avg time: 92.9s
Game Dev
Top 26%
1,242Elo
Win rate: 59.3%Avg time: 126s
SVG
Top 33%
1,180Elo
Win rate: 58.7%Avg time: 31.9s
UI Component
Top 28%
1,245Elo
Win rate: 58.1%Avg time: 99.9s
Website
Top 25%
1,253Elo
Win rate: 59.7%Avg time: 136s
Android Native
Top 46%
1,191Elo
Win rate: 65.5%
Full-Stack
Top 57%
1,155Elo
Win rate: 60.2%
Mobile Apps
Top 43%
1,186Elo
Win rate: 60.7%
Web Apps
Top 64%
1,152Elo
Win rate: 55.1%

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": "anthropic/claude-opus-4.5: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="anthropic/claude-opus-4.5: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: "anthropic/claude-opus-4.5:batch",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Anthropic: Claude Opus 4.5 (batch) API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Anthropic: Claude Opus 4.5 (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.
Create an accountBuy Claude 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

Updated 2026-10-13