Hormouz AIHormouzSign in

Anthropic: Claude Sonnet 4: AI model

Claude Sonnet 4 is a balanced default for production coding, agents and general work from Anthropic, with a 1M-token context window. Reachable from inside Iran through Hormouz.

Context window:
200,000 tokens
Input:
$3/1M tokens
Output:
$15/1M tokens
Type:
text, image
  • Vision
  • Tools
  • Streaming
  • Long context

Thinking levels:

Claude Sonnet 4 is the balanced tier of the Claude family, tuned to pair strong coding and reasoning with everyday cost-efficiency. 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.

Sonnet-class models are commonly used for production coding, agentic workflows, document drafting, data analysis and everyday assistant tasks. 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: $3 per million input tokens and $15 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.

Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...

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-4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorAnthropic
TypeText, Image
Context window200,000 tokens
Pricing$3.00/M in · $15.00/M out
APIChat Completions
CapabilitiesStreaming · Vision · Tools

Benchmarks

37.6
Coding Index
Better than 39% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
77.7%
HLE
Humanity's Last Exam
10.7%
IFBench
Instruction-following
54.7%
AA-LCR
Long-context reasoning
70.3%
CritPt
Research-level physics reasoning
0.3%
AA Omniscience
Broad factual knowledge accuracy
22.7%
Non-Hallucination
Rate of avoiding fabricated answers
70.9%

Coding

Terminal-Bench Hard
Agentic coding & terminal use
31.1%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
64.6%
GDPval
Economically valuable tasks
9.7%

Source: Artificial Analysis

3D
Top 50%
1,150Elo
Win rate: 57.8%Avg time: 57.0s
Code
Top 65%
1,147Elo
Win rate: 53.4%Avg time: 72.9s
Data Viz
Top 72%
1,120Elo
Win rate: 53.2%Avg time: 60.5s
Game Dev
Top 60%
1,146Elo
Win rate: 55.4%Avg time: 79.0s
SVG
Top 79%
1,062Elo
Win rate: 47.8%Avg time: 17.0s
UI Component
Top 65%
1,135Elo
Win rate: 57.9%Avg time: 59.6s
Website
Top 63%
1,152Elo
Win rate: 52.4%Avg time: 74.8s

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-4",
    "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-4",
    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-4",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Anthropic: Claude Sonnet 4 API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Anthropic: Claude Sonnet 4 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 4 cost?
Billing is usage-based: $3 per million input tokens and $15 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
How do I access Claude Sonnet 4 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 Sonnet 4 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 Sonnet 4 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 Sonnet 4 good for?
Typical uses are production coding, agentic workflows, document drafting, data analysis and everyday assistant tasks.
How does Claude Sonnet 4 compare to other Claude models?
Claude comes in three tiers: Opus, Sonnet and Haiku. Sonnet is the balanced tier: strong coding and reasoning at a lower cost than Opus, a common production default.

Updated 2026-10-13