Hormouz AIHormouzSign in

Qwen: Qwen3.7 Plus: AI model

Qwen3.7 Plus is a cost-effective model in the Qwen3.7 series that accepts text and image input, with multimodal agentic capabilities for coding and productivity. Reachable from inside Iran through Hormouz.

Context window:
1,000,000 tokens
Input:
$0.32/1M tokens
Output:
$1.28/1M tokens
Type:
text, image
  • Vision
  • Tools
  • Streaming
  • Long context

Thinking levels:

Qwen3.7-Plus is a cost-effective model in the Qwen3.7 series that accepts text and image input and produces text output. It builds on the series' text capabilities with a broad upgrade to its vision-language abilities while retaining agent-level intelligence for coding, tool use and productivity workflows.

Its distinguishing trait is multimodal interactive hybrid-agent capability: it can perceive real-world scenes, read screens and interact with GUIs, generate code from visual references and perform end-to-end navigation within mobile apps. Its 1M-token context window suits large contexts. Hormouz exposes an OpenAI-compatible API. Point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs unchanged.

Pricing is usage-based: $0.32/M in · $1.28/M out. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.7-plus",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorQwen
TypeText, Image
Context window1,000,000 tokens
Pricing$0.32/M in · $1.28/M out
APIChat Completions
CapabilitiesStreaming · Vision · Tools

Benchmarks

25.2
Intelligence Index
Better than 48% of models we compared
55.9
Coding Index
Better than 62% of models we compared
17.5
Agentic Index
Better than 46% of models we compared

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
90%
HLE
Humanity's Last Exam
35.6%
IFBench
Instruction-following
78%
AA-LCR
Long-context reasoning
73%
CritPt
Research-level physics reasoning
9.1%
AA Omniscience
Broad factual knowledge accuracy
22.5%
Non-Hallucination
Rate of avoiding fabricated answers
72.3%

Coding

SciCode
Python for scientific computing
46.1%
Terminal-Bench Hard
Agentic coding & terminal use
47%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
93%
GDPval
Economically valuable tasks
13.5%

Source: Artificial Analysis

Design Arena

How Design Arena works ↗
3D
Top 24%
1,248Elo
Win rate: 48.5%Avg time: 173s
ASCII Art
Top 65%
1,142Elo
Win rate: 40.8%Avg time: 231s
Code
Top 18%
1,274Elo
Win rate: 50.5%Avg time: 268s
Data Viz
Top 13%
1,284Elo
Win rate: 51.2%Avg time: 231s
Game Dev
Top 20%
1,273Elo
Win rate: 49.7%Avg time: 245s
SVG
Top 24%
1,212Elo
Win rate: 47.6%Avg time: 113s
UI Component
Top 25%
1,264Elo
Win rate: 48.9%Avg time: 222s
Website
Top 16%
1,277Elo
Win rate: 51%Avg time: 312s

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": "qwen/qwen3.7-plus",
    "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="qwen/qwen3.7-plus",
    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: "qwen/qwen3.7-plus",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Qwen: Qwen3.7 Plus API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Qwen: Qwen3.7 Plus 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 account

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 Qwen3.7 Plus cost?
Billing is usage-based: $0.32/M in · $1.28/M out. There is no fixed monthly fee. You pay only for what you use.
How do I use Qwen3.7 Plus from inside Iran?
Create a Hormouz account and generate an API key. Hormouz gives you a stable route to the model from inside Iran, with no foreign credit card or circumvention tooling needed.
Is Qwen3.7 Plus OpenAI-compatible?
Yes. Hormouz serves an OpenAI-compatible API. Point your base URL at Hormouz and swap in a Hormouz key; your existing SDKs and code work without a rewrite.
What inputs does Qwen3.7 Plus accept?
It accepts text and image input and produces text output, suiting multimodal and agentic tasks.
What is Qwen3.7 Plus good for?
Coding, tool use, screen reading and GUI interaction, generating code from visual references and productivity tasks.
How large is Qwen3.7 Plus's context window?
The context window is up to 1M tokens, and the model supports tool calling.

Updated 2026-10-13