Hormouz AIHormouzSign in

Anthropic: Claude Opus 5: AI model

Claude Opus 5 is Anthropic's previous flagship for hard reasoning, coding and agent work from Anthropic with a 1M-token context window. Reachable from inside Iran through Hormouz.

Context window:
1,000,000 tokens
Input:
$5/1M tokens
Output:
$25/1M tokens
Type:
text, image
  • Vision
  • Tools
  • Streaming
  • Long context

Thinking levels: max · xhigh · high · medium · low

Claude Opus 5 was Anthropic's flagship before Claude Opus 5.5. It is strong at end-to-end software tasks, code review and bug finding, reading charts and documents, complex office deliverables and coordinating sub-agents working in parallel. It keeps following instructions and using tools well over long tasks, and still performs at lower effort settings when speed and token cost matter.

It accepts text, image and file (PDF) input and returns text, and supports tool calling, structured JSON output and streaming. Reasoning can be switched on when a problem needs more thought and left off when speed matters. Claude Opus 5 is commonly used for end-to-end software tasks, code review, chart and document analysis, office deliverables and multi-agent coordination. Hormouz serves it behind an OpenAI-compatible API: point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs without changes.

Pricing is usage-based: $5 per million input tokens and $25 per million output tokens. There is no fixed monthly fee, and you pay only for the tokens you use. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...

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-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorAnthropic
TypeText, Image
Context window1,000,000 tokens
Pricing$5.00/M in · $25.00/M out
APIChat Completions
CapabilitiesStreaming · Vision · Tools

Benchmarks

49.7
Intelligence Index
Better than 94% of models we compared
77
Coding Index
Better than 97% of models we compared
55.6
Agentic Index
Better than 97% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
93.7%
HLE
Humanity's Last Exam
54.4%
AA-LCR
Long-context reasoning
80.3%
CritPt
Research-level physics reasoning
27.7%
AA Omniscience
Broad factual knowledge accuracy
59.5%
Non-Hallucination
Rate of avoiding fabricated answers
40.5%

Coding

SciCode
Python for scientific computing
55.7%

Agentic

GDPval
Economically valuable tasks
59.6%

Source: Artificial Analysis

Ranking distribution

First
4,166
Second
3,083
Third
1,520
Fourth
1,008

9777 tournaments ?

Agentic Game Dev
Top 8%
1,261Elo
Win rate: 53.8%
Android Native
Top 8%
1,269Elo
Win rate: 55.9%
Full-Stack
Top 9%
1,305Elo
Win rate: 57.3%
Godot Game Dev
Top 8%
1,279Elo
Win rate: 54.2%
Mobile Apps
Top 2%
1,348Elo
Win rate: 67.1%
Python Slides
Top 15%
1,267Elo
Win rate: 54.4%
Web Apps
Top 19%
1,259Elo
Win rate: 54.5%
3D
Top 6%
1,344Elo
Win rate: 61.2%Avg time: 332s
ASCII Art
Top 1%
1,357Elo
Win rate: 67.8%Avg time: 244s
Code
Top 4%
1,330Elo
Win rate: 57.9%Avg time: 312s
Data Viz
Top 4%
1,344Elo
Win rate: 60.7%Avg time: 227s
Game Dev
Top 3%
1,350Elo
Win rate: 59.1%Avg time: 382s
SVG
Top 3%
1,313Elo
Win rate: 58.6%Avg time: 104s
UI Component
Top 3%
1,350Elo
Win rate: 60.5%Avg time: 218s
Website
Top 5%
1,315Elo
Win rate: 56.1%Avg time: 306s

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-5",
    "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-5",
    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-5",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Anthropic: Claude Opus 5 API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Anthropic: Claude Opus 5 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

FAQ

How much does Claude Opus 5 cost?
Pricing is usage-based: $5 per million input tokens and $25 per million output tokens. There is no fixed monthly fee, and you pay only for the tokens you use.
How do I access Claude Opus 5 from inside Iran?
Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Is Claude Opus 5 compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Point your base URL at Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
What context window and capabilities does Claude Opus 5 have?
It has a 1M-token context window, accepts text, image and file (PDF) input, and supports tool calling, structured JSON output and streaming. Reasoning can be switched on when a problem needs more thought and left off when speed matters.
What is Claude Opus 5 good for?
Typical uses are end-to-end software tasks, code review, chart and document analysis, office deliverables and multi-agent coordination.

Updated 2026-10-13