Qwen3.7 plus

qwen3.7-plus

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input as well as text output. Building on the series' text capabilities, it delivers a comprehensive upgrade to visual language abilities while retaining full-stack, agent-level intelligence for coding, tool use, and productivity workflows. Its standout feature is the multimodal interactive hybrid agent capability: it can perceive real-world scenes, read screens and interact with GUI, generate code from visual references, and perform end-to-end navigation in mobile applications.

Context window1.0M

Provider通义千问

Released2026/06/29

Playground

Pricing

The same model is available through multiple service channels — choose based on latency, reliability and cost.

Prices in $ / 1M tokens

To pick a channel, add a provider field to the request body, for example "provider": { "channel": "direct" }. Valid values are direct / stable / economical; omit it to use the default channel.

Direct

Direct upstream connection — best when you need native behavior and the full context window.

Input context	Input	Output
≤ 256K	0.29/M	1.18/M
> 256K	0.88/M	3.53/M

Overview

Input

Text

Output

Text

Qwen3.7-Plus API: A Multimodal Hybrid Agent That Can See Screens and Operate Interfaces

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series, featuring a dense architecture. It supports text and image input and text output. Building on the series' text capabilities, it delivers a comprehensive upgrade to vision-language capabilities while retaining full-stack agent-level intelligence for coding, tool use, and productivity workflows.

Its most distinctive feature is multimodal interactive hybrid agent capability: it can perceive real-world scenes, read screens and interact with GUIs, extract task elements from visual information, and drive subsequent execution. In the Arena AI comprehensive benchmark, Qwen3.7-Plus-Preview scored 1156, close to Claude Opus 4.7's 1189.

SeaWhale AI provides Qwen3.7-Plus through an OpenAI-compatible interface, supporting multimodal input, tool calling, and streaming output.

Get API Key · Model ID: qwen3.7-plus

Why Choose Qwen3.7-Plus

Multimodal interactive hybrid agent — reads screens and interacts with GUIs
Arena AI score of 1156 — close to Claude Opus 4.7's 1189
Cost-effective dense architecture — significantly cheaper than the flagship Max tier, with full-stack capabilities
1M token context — fits long documents and large repositories at once
All-domain thinking mode — unified reasoning chain for text, images, and code

Core Capabilities

01 Screen Understanding and GUI Interaction

This is Qwen3.7-Plus's most distinctive capability: it can read screen content, understand interface structure, identify operable elements, and drive subsequent actions such as clicks and inputs. This frees vision-based automation from relying on fragile selectors.

Interface element recognition and semantic understanding
Operation path planning
Vision-based automated testing

02 Real-World Scene Perception

Beyond screens, it can also understand real-world image scenes — device status, environmental layout, chart data — and convert visual information into executable task elements.

On-site image assessment and classification
Chart data extraction
Scene-understanding-driven decision-making

03 Full-Stack Agent Intelligence

While upgrading multimodal capabilities, Qwen3.7-Plus retains complete coding, tool use, and productivity workflow capabilities, making it a well-balanced general-purpose agent foundation.

Coding and code understanding
Multi-tool orchestration
Office and productivity tasks

04 All-Domain Thinking Mode

The Qwen3.7 series is the first to achieve a unified reasoning chain for text, images, and code, breaking through the limitation of previous models that only supported text thinking chains.

Cross-modal unified reasoning
Mixed text-image problem solving
Visual information participating in the thinking process

Best Use Cases

Scenario	Description
GUI automation	Read screens, assess states, drive operations
Visual testing	Automated testing based on interface understanding
Multimodal customer service	Problem diagnosis after users send screenshots
On-site quality inspection	Image assessment and subsequent action triggering
Text-image document processing	Chart, table, and mixed-layout document parsing
Cost-effective agents	Scenarios that need multimodal capabilities but have limited budgets

Differences Between Qwen3.7-Plus, Qwen3.7-Max, and Qwen3.6-Plus

Capability	Qwen3.7-Plus	Qwen3.7-Max	Qwen3.6-Plus
Model ID	`qwen3.7-plus`	`qwen3.7-max`	`qwen3.6-plus`
Architecture	Dense	Trillion-parameter MoE	Hybrid architecture
Input modalities	Text, image	Text	Text, image
Context window	1M tokens	1M tokens	1M tokens
Max output	128K tokens	128K tokens	65.5K tokens
Arena AI	1156	1284	—
Focus	Screen understanding and GUI interaction	Agentic coding and autonomous execution	Agentic coding and frontend

Specific pricing is subject to the real-time price card at the top of the page.

How to Use the Qwen3.7-Plus API

1. Create a SeaWhale AI API key Generate a key in the console and top up your balance.

2. Treat vision as decision input Qwen3.7-Plus's value lies in "what to do after seeing." Clearly state the target action in the prompt, rather than just asking for an image description.

3. Call the API

curl -X POST https://api.seawhaleai.com/v1/chat/completions \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "qwen3.7-plus",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "image_url", "image_url": {"url": "https://example.com/screen.png"}},
        {"type": "text", "text": "What state is the current page in? Which elements still need to be clicked to complete the order?"}
      ]
    }],
    "stream": true
  }'

FAQ

How do I choose between Plus and Max? Choose Plus if you need image input, screen understanding, or GUI interaction; choose Max for text-only agentic coding and long-term autonomous execution. Plus also offers better value for money.

What does "hybrid agent" mean? It means the model can handle both visual perception and action execution — it not only understands images, but can also drive subsequent operations based on that understanding, forming a complete closed loop.

What level is an Arena AI score of 1156? It's close to Claude Opus 4.7's 1189, placing it in the top tier among multimodal models.

What are the context and output limits? 1M token context, with a maximum output of 128K tokens.

What is the all-domain thinking mode for? It allows image information to participate directly in the reasoning process, rather than converting it to text descriptions first. This yields higher accuracy on mixed text-image problems.

Is it suitable for GUI automation? Yes. Vision-understanding-based automation is more robust than solutions that rely on DOM selectors, and it is less likely to break after UI redesigns.

Why Choose SeaWhale AI for the Qwen3.7-Plus API

No Alibaba Cloud account required — call directly with a single key
OpenAI-compatible interface — multimodal request format consistent with OpenAI
Side-by-side multimodal model comparison — compare performance with Gemini, GLM-5V, and 豆包 under the same account
RMB settlement — domestic models are priced in RMB

API

API integration

Model IDUse this value as the model in inference requests

qwen3.7-plus

API KeyBearer token used to authenticate inference requests

Manage API keys

Base URLOpenAI compatible · /chat/completions

https://api.seawhaleai.com/v2/

provider OptionalSelects a service channel; omit it and the system picks the default

"provider": { "channel": "direct" }

qwen3.7-plus usage examples

SeaWhale AI is compatible with the OpenAI API protocol, so you can call it with the OpenAI SDK or plain HTTP requests. Streaming is enabled by default.

About the provider parameter (optional, a SeaWhale AI extension): most models are served over several channels that differ slightly in price and reliability. Add a provider field to the request body to pick one; omit it and the system selects the default channel — normal calls are unaffected.

provider is not part of the official OpenAI protocol — it is a SeaWhale AI extension that only takes effect on this platform. The OpenAI SDK allows custom fields like this to pass through; see the examples below.

Value	Channel	Best for
`direct`	Direct	The official upstream link, for native behavior and the full context window
`stable`	Preferred	Balanced availability and speed — a good default for production traffic
`economical`	Economy	Cost first, well suited to batch processing and price-sensitive workloads

Available channels and their prices are listed under "Pricing" above (channels vary by model). Additional notes:

Syntax: "provider": { "channel": "direct" }.
If the requested channel is not enabled for that model, the request automatically falls back to the default channel and returns normally — it does not error.
With the official SDKs: in Python pass it via extra_body; in Node.js put it directly on the request object and it passes through. In TypeScript projects, add a // @ts-expect-error line to skip the type check.

cURLPythonNode.js

curl https://api.seawhaleai.com/v2/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <API_KEY>" \
  -d '{
    "model": "qwen3.7-plus",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
    "provider": { "channel": "direct" },
    "stream": true
  }'
# provider is optional — remove this line to use the default channel

from openai import OpenAI

client = OpenAI(
    base_url="https://api.seawhaleai.com/v2",
    api_key="<API_KEY>",
)

stream = client.chat.completions.create(
    model="qwen3.7-plus",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"},
    ],
    stream=True,
    # Optional: pick a service channel; omit to use the default
    extra_body={"provider": {"channel": "direct"}},
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.seawhaleai.com/v2',
  apiKey: '<API_KEY>',
})

const stream = await client.chat.completions.create({
  model: 'qwen3.7-plus',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Hello!' },
  ],
  stream: true,
  // Optional: pick a service channel; omit to use the default
  // @ts-expect-error provider is a SeaWhale AI extension, not in the OpenAI SDK types
  provider: { channel: 'direct' },
})

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '')
}