Hormouz AIHormouzSign in

Anthropic: Claude Sonnet 5: AI model

Claude Sonnet 5 is Anthropic's most capable Sonnet-class model, with a 1M-token context, adaptive thinking and text/image/file input. Served through Hormouz with stable access from inside Iran.

Context window:
1,000,000 tokens
Input:
$2/1M tokens
Output:
$10/1M tokens
Type:
text, image
  • Vision
  • Tools
  • Streaming
  • Long context
Good for:Popular for Finance · #14Popular for Legal · #15Ranks are based on global usage data

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

Claude Sonnet 5 is a frontier model from Anthropic aimed at coding, agents and professional knowledge work. It supports adaptive thinking with selectable reasoning-effort levels (low through max), so you can trade latency for depth on hard problems, and it accepts text, image and file inputs with a 1M-token context window.

The large context makes it well-suited to whole-codebase edits, long research documents and multi-step agent runs, while its tool-calling and structured-output support let it drive real workflows rather than just chat.

Pricing is usage-based: $2 per million input tokens and $10 per million output tokens. Hormouz provides stable access to Claude Sonnet 5 from inside Iran, with no foreign credit card or circumvention tooling required.

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

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

Specs

VendorAnthropic
TypeText, Image
Context window1,000,000 tokens
Pricing$2.00/M in · $10.00/M out
APIChat Completions
CapabilitiesStreaming · Vision · Tools

Benchmarks

28.1
Intelligence Index
Better than 54% of models we compared

Reasoning

HLE
Humanity's Last Exam
30%
AA-LCR
Long-context reasoning
73.7%
CritPt
Research-level physics reasoning
8.6%
AA Omniscience
Broad factual knowledge accuracy
37.1%
Non-Hallucination
Rate of avoiding fabricated answers
30.1%

Coding

SciCode
Python for scientific computing
51.6%

Agentic

GDPval
Economically valuable tasks
33%

Source: Artificial Analysis

Agentic Game Dev
Top 29%
1,226Elo
Win rate: 52.3%
Android Native
Top 24%
1,237Elo
Win rate: 54.4%
Full-Stack
Top 23%
1,248Elo
Win rate: 53.7%
Godot Game Dev
Top 36%
1,225Elo
Win rate: 54.4%
HTML Slides
Top 22%
1,217Elo
Win rate: 53.7%
Mobile Apps
Top 26%
1,216Elo
Win rate: 51.5%
Python Slides
Top 41%
1,216Elo
Win rate: 50.1%
Web Apps
Top 26%
1,237Elo
Win rate: 53.3%
3D
Top 17%
1,272Elo
Win rate: 54.4%Avg time: 218s
ASCII Art
Top 25%
1,221Elo
Win rate: 52.1%Avg time: 58.4s
Code
Top 14%
1,283Elo
Win rate: 53.2%Avg time: 199s
Data Viz
Top 23%
1,256Elo
Win rate: 52.7%Avg time: 139s
Game Dev
Top 12%
1,296Elo
Win rate: 53%Avg time: 325s
SVG
Top 29%
1,191Elo
Win rate: 50%Avg time: 57.5s
UI Component
Top 17%
1,286Elo
Win rate: 54.3%Avg time: 134s
Website
Top 14%
1,283Elo
Win rate: 52.9%Avg time: 175s

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

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

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Anthropic: Claude Sonnet 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 Sonnet 5 cost?
Billing is usage-based: $2 per million input tokens and $10 per million output tokens. There is no fixed monthly fee. You pay only for what you use, at the rates shown in the Hormouz dashboard.
How do I access Claude Sonnet 5 from inside Iran?
Create an account on Hormouz and generate an API key. Hormouz provides a stable path to Claude Sonnet 5 from inside Iran, with no foreign credit card or circumvention tooling required.
Is Claude Sonnet 5 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 OpenAI SDKs and code run without a rewrite.
How large is the Claude Sonnet 5 context window?
Claude Sonnet 5 supports a 1M-token context window and accepts text, image and file inputs, so it can work over large codebases and long documents in a single request.

Updated 2026-10-13