Hormouz AIHormouzSign in

DeepSeek: R1: AI model

DeepSeek R1 is an open-source reasoning model with 671B parameters (37B active) and fully open reasoning tokens, delivering performance on par with leading reasoning models, via Hormouz.

Context window:
64,000 tokens
Input:
$0.7/1M tokens
Output:
$2.5/1M tokens
Type:
text
  • Tools
  • Streaming

Thinking levels: Always thinks

DeepSeek R1 is an open-source reasoning model built with 671 billion parameters and 37 billion active per pass. Its distinguishing feature is fully open reasoning tokens. The model’s chain of thought is exposed, so you can see its reasoning steps.

The model is built for hard reasoning, math and coding tasks and reaches performance on par with leading reasoning models on many benchmarks, but it is released open-source. It carries a wide context window and can be freely redistributed and commercialized.

Pricing is usage-based: $1.485/M in · $5.94/M out. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-r1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorDeepSeek
TypeText
Context window64,000 tokens
Pricing$0.70/M in · $2.50/M out
APIChat Completions
CapabilitiesStreaming · Tools

Benchmarks

11.4
Intelligence Index
Better than 18% of models we compared
24.6
Coding Index
Better than 26% of models we compared
1.1
Agentic Index
Better than 15% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
70.8%
HLE
Humanity's Last Exam
8.5%
IFBench
Instruction-following
39%
AA-LCR
Long-context reasoning
57.7%
CritPt
Research-level physics reasoning
0.6%
AA Omniscience
Broad factual knowledge accuracy
30.5%
Non-Hallucination
Rate of avoiding fabricated answers
9.7%

Coding

SciCode
Python for scientific computing
38.3%
Terminal-Bench Hard
Agentic coding & terminal use
6.1%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
11.4%
GDPval
Economically valuable tasks
0%

Source: Artificial Analysis

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": "deepseek/deepseek-r1",
    "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="deepseek/deepseek-r1",
    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: "deepseek/deepseek-r1",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the DeepSeek: R1 API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches DeepSeek: R1 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 DeepSeek 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 this model cost?
Billing is usage-based: $1.485 per million input tokens and $5.94 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
What makes DeepSeek R1 distinctive?
DeepSeek R1 is an open-source reasoning model with fully open reasoning tokens, meaning you can see the model’s chain of thought. It suits hard reasoning, math and coding tasks.
What is DeepSeek R1 good for?
Complex reasoning problems, mathematics, coding and any task that benefits from step-by-step thinking.
How do I access this model 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 required.
Is this model compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key, and your existing SDKs run without a rewrite.

Updated 2026-10-13