Hormouz AIHormouzSign in

Anthropic: Claude Opus 4.6: AI model

Claude Opus 4.6 is a maximum-capability model for demanding engineering and multi-step agent tasks 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 · high · medium · low

Claude Opus 4.6 is the top-capability tier of the Claude family, aimed at the hardest coding, reasoning and long-horizon agentic work. It accepts text and image input and returns text, supports tool calling for building agents and automations, and works with streaming responses. It also supports extended reasoning, so you can trade extra thinking time for higher accuracy on hard problems. The context window is 1M tokens, which suits long documents, large codebases and multi-turn sessions.

Opus-class models are commonly used for complex software engineering, large-codebase refactors, multi-step debugging, long-running agent pipelines and demanding knowledge work. Hormouz serves it behind an OpenAI-compatible API, so you can point your base URL at Hormouz, drop in a Hormouz key, and run existing OpenAI SDK code without changes.

Pricing is usage-based: $5 per million input tokens and $25 per million output tokens. There is no fixed monthly fee. 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.

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...

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-4.6",
    "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

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
84%
HLE
Humanity's Last Exam
19.1%
IFBench
Instruction-following
44.6%
AA-LCR
Long-context reasoning
67%
CritPt
Research-level physics reasoning
2.8%
AA Omniscience
Broad factual knowledge accuracy
45.8%
Non-Hallucination
Rate of avoiding fabricated answers
19.9%

Coding

Terminal-Bench Hard
Agentic coding & terminal use
48.5%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
84.8%

Source: Artificial Analysis

Agentic Game Dev
Top 33%
1,213Elo
Win rate: 50%
Android Native
Top 32%
1,215Elo
Win rate: 63.8%
Full-Stack
Top 32%
1,218Elo
Win rate: 59.8%
Mobile Apps
Top 35%
1,204Elo
Win rate: 59.2%
Web Apps
Top 48%
1,199Elo
Win rate: 57%
3D
Top 13%
1,285Elo
Win rate: 62.5%Avg time: 156s
ASCII Art
Top 21%
1,264Elo
Win rate: 62.9%Avg time: 72.3s
Code
Top 11%
1,295Elo
Win rate: 61.2%Avg time: 191s
Data Viz
Top 11%
1,289Elo
Win rate: 58.7%Avg time: 153s
Game Dev
Top 14%
1,285Elo
Win rate: 60.5%Avg time: 198s
SVG
Top 23%
1,214Elo
Win rate: 60.5%Avg time: 55.7s
UI Component
Top 14%
1,291Elo
Win rate: 59.8%Avg time: 144s
Website
Top 9%
1,298Elo
Win rate: 61.2%Avg time: 209s

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-4.6",
    "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-4.6",
    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-4.6",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Anthropic: Claude Opus 4.6 API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Anthropic: Claude Opus 4.6 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 4.6 cost?
Billing is usage-based: $5 per million input tokens and $25 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
How do I access Claude Opus 4.6 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 4.6 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 4.6 have?
It has a 1M-token context window, accepts text and image input, and supports tool calling and streaming, plus extended reasoning for harder problems. That makes it suitable for long documents, codebases and agentic workflows.
What is Claude Opus 4.6 good for?
Typical uses are complex software engineering, large-codebase refactors, multi-step debugging, long-running agent pipelines and demanding knowledge work.
How does Claude Opus 4.6 compare to other Claude models?
Claude comes in three tiers: Opus, Sonnet and Haiku. Opus is the highest-capability tier: the pick for the hardest reasoning, coding and long-horizon agent work.

Updated 2026-10-13