Hormouz AIHormouzSign in

DeepSeek: DeepSeek V4 Flash 0731: AI model

DeepSeek V4 Flash 0731 is the stable release of DeepSeek V4 Flash from DeepSeek with a 1M-token context window. Reachable from inside Iran through Hormouz.

Context window:
1,048,576 tokens
Input:
$0.02/1M tokens
Output:
$0.64/1M tokens
Type:
text
  • Tools
  • Streaming
  • Long context
Good for:Popular for Translation · #1Popular for Finance · #3Popular for Science · #4Popular for Technology · #4Ranks are based on global usage data

Thinking levels: max · high · low

DeepSeek V4 Flash 0731 is the generally available release of DeepSeek V4 Flash, re-post-trained for coding, reasoning and agent workflows. It is a sparse mixture-of-experts with 13B active parameters out of 284B and a 1M-token context, and its input price is among the lowest of any capable model.

It accepts text input and returns text, and supports tool calling, structured JSON output and streaming. Reasoning can be switched on when a problem needs more thought and left off when speed matters. DeepSeek V4 Flash 0731 is commonly used for low-cost coding, reasoning, agents with long prompts and bulk text processing. Hormouz serves it behind an OpenAI-compatible API: point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs without changes.

Pricing is usage-based: $0.015 per million input tokens and $1.28 per million output tokens. There is no fixed monthly fee, and 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.

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

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-v4-flash-0731",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorDeepSeek
TypeText
Context window1,048,576 tokens
Pricing$0.02/M in · $0.64/M out
APIChat Completions
CapabilitiesStreaming · Tools

Benchmarks

34.3
Intelligence Index
Better than 67% of models we compared
69.1
Coding Index
Better than 79% of models we compared
41
Agentic Index
Better than 79% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
90.8%
HLE
Humanity's Last Exam
38.6%
AA-LCR
Long-context reasoning
79.7%
CritPt
Research-level physics reasoning
16.6%
AA Omniscience
Broad factual knowledge accuracy
40.4%
Non-Hallucination
Rate of avoiding fabricated answers
8.3%

Coding

SciCode
Python for scientific computing
50.3%

Agentic

GDPval
Economically valuable tasks
46.9%

Source: Artificial Analysis

Design Arena

How Design Arena works ↗
3D
Top 31%
1,219Elo
Win rate: 48.6%Avg time: 255s
ASCII Art
Top 90%
1,100Elo
Win rate: 33.3%Avg time: 320s
Code
Top 30%
1,236Elo
Win rate: 46.4%Avg time: 250s
Data Viz
Top 47%
1,190Elo
Win rate: 41.1%Avg time: 241s
Game Dev
Top 31%
1,221Elo
Win rate: 44.6%Avg time: 293s
SVG
Top 31%
1,186Elo
Win rate: 45.1%Avg time: 220s
UI Component
Top 30%
1,242Elo
Win rate: 46.8%Avg time: 229s
Website
Top 27%
1,245Elo
Win rate: 46.7%Avg time: 239s

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": "deepseek/deepseek-v4-flash-0731",
    "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-v4-flash-0731",
    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-v4-flash-0731",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the DeepSeek: DeepSeek V4 Flash 0731 API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches DeepSeek: DeepSeek V4 Flash 0731 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 DeepSeek V4 Flash 0731 cost?
Pricing is usage-based: $0.015 per million input tokens and $1.28 per million output tokens. There is no fixed monthly fee, and you pay only for the tokens you use.
How do I access DeepSeek V4 Flash 0731 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 DeepSeek V4 Flash 0731 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 DeepSeek V4 Flash 0731 have?
It has a 1M-token context window, accepts text input, and supports tool calling, structured JSON output and streaming. Reasoning can be switched on when a problem needs more thought and left off when speed matters.
What is DeepSeek V4 Flash 0731 good for?
Typical uses are low-cost coding, reasoning, agents with long prompts and bulk text processing.

Updated 2026-10-13