Anthropic: Claude Sonnet 4.6 (batch): AI model
- Context window:
- 1,000,000 tokens
- Input:
- $1.5/1M tokens
- Output:
- $7.5/1M tokens
- Type:
- text, image
- Vision
- Tools
- Streaming
- Long context
Thinking levels: max · high · medium · low
Anthropic: Claude Sonnet 4.6 (batch) is a AI model from Anthropic, available through Hormouz via an OpenAI-compatible API with stable access from inside Iran.
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...
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-4.6:batch",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | Anthropic |
|---|---|
| Type | Text, Image |
| Context window | 1,000,000 tokens |
| Pricing | $1.50/M in · $7.50/M out |
| API | Chat Completions |
| Capabilities | Streaming · Vision · Tools |
Benchmarks
30.1
Intelligence Index
Better than 57% of models we compared
63
Coding Index
Better than 72% of models we compared
31.8
Agentic Index
Better than 70% of models we compared
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
87.5%
HLE
Humanity's Last Exam
33.6%
IFBench
Instruction-following
56.6%
AA-LCR
Long-context reasoning
80%
CritPt
Research-level physics reasoning
3.1%
AA Omniscience
Broad factual knowledge accuracy
40.9%
Non-Hallucination
Rate of avoiding fabricated answers
51.6%
Coding
SciCode
Python for scientific computing
50.1%
Terminal-Bench Hard
Agentic coding & terminal use
53%
Agentic
τ²-Bench
Tool-use agents in dual-control scenarios
75.7%
GDPval
Economically valuable tasks
36.7%
Source: Artificial Analysis
Design Arena
How Design Arena works ↗Ranking distribution
First
9,265
Second
6,979
Third
2,827
Fourth
1,134
20205 tournaments ?
Agentic Game Dev
Top 67%1,177Elo
Win rate: 52.2%
Android Native
Top 35%1,211Elo
Win rate: 62%
Full-Stack
Top 34%1,211Elo
Win rate: 64.3%
Godot Game Dev
Top 33%1,226Elo
Win rate: 60.6%
Mobile Apps
Top 30%1,209Elo
Win rate: 63.6%
Web Apps
Top 57%1,183Elo
Win rate: 57%
3D
Top 26%1,245Elo
Win rate: 57.6%Avg time: 133s
ASCII Art
Top 22%1,246Elo
Win rate: 60.1%Avg time: 85.9s
Code
Top 16%1,282Elo
Win rate: 59.4%Avg time: 177s
Data Viz
Top 12%1,287Elo
Win rate: 58.2%Avg time: 139s
Game Dev
Top 21%1,272Elo
Win rate: 58.8%Avg time: 179s
SVG
Top 26%1,196Elo
Win rate: 58.7%Avg time: 56.4s
UI Component
Top 19%1,278Elo
Win rate: 58.3%Avg time: 149s
Website
Top 11%1,291Elo
Win rate: 60%Avg time: 200s
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-4.6: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-sonnet-4.6: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-sonnet-4.6:batch",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the Anthropic: Claude Sonnet 4.6 (batch) API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches Anthropic: Claude Sonnet 4.6 (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.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessUpdated 2026-10-13