Velokey

Qwen3.7 Plus

阿里巴巴Chatin 60 · out 60 Credits / 1M tokens≈$60 / $60Available
Get API keyAPI docs

Qwen3.7-Plus is Alibaba's multimodal agent model with screen perception, GUI grounding, a 1M-token context, and preserve_thinking. Access it through Velokey's unified endpoint with below-list pricing.

1M-token contextScreen perception + GUI groundingpreserve_thinking across tool callsLow-cost multimodal agent

Use cases

Screen perception & visual UI testing · Browser automation & RPA

Input

Text, image

Output

Text

Billing

Per token

Model Type:
0.7
02
2048
2568192
qwen3.7-plus

Start a conversation

Type a message below to begin

Sign up to get $0.5 in free credits — about 20 free images

Pricing details

Transparent usage-based pricing with no hidden fees.

Detailed Pricing

Tiered pricing

Usage-based pricing breakdown

<= 256K tokensContext length ≤ 256K
SpecPriceOfficialSavings
Input/1M tokens0.32 Credits≈$0.320.4 Credits-20%
Output/1M tokens1.28 Credits≈$1.281.6 Credits-20%
Cache Read/1M tokens0.032 Credits≈$0.0320.04 Credits-20%
Cache Write/1M tokens0.4 Credits≈$0.40.5 Credits-20%
> 256K tokensContext length > 256K
SpecPriceOfficialSavings
Input/1M tokens0.96 Credits≈$0.961.2 Credits-20%
Output/1M tokens3.84 Credits≈$3.844.8 Credits-20%
Cache Read/1M tokens0.096 Credits≈$0.0960.12 Credits-20%
Cache Write/1M tokens1.2 Credits≈$1.21.5 Credits-20%

Billing Rules

  • Output price varies by model, resolution, quality, duration, or token usage.
  • Uploaded reference files may be charged separately when supported.
  • Add-on capabilities such as web search or image search may be billed per request.
  • Token-based models are billed by input and output tokens.
  • If the primary route is unavailable, Velokey may automatically switch to a stable fallback route when possible.
  • Usage is pay-as-you-go with transparent credit deduction.

* Final cost depends on the generated result.

Related models

Explore other models in the same family.

Affordable Qwen3.7-Plus API

Access Alibaba's Qwen3.7-Plus on Velokey — multimodal screen perception, GUI grounding, a 1M-token context, and preserve_thinking, with a unified endpoint and below-list pricing for production agent apps.

Meet Qwen3.7-Plus and its API access

Qwen3.7-Plus is Alibaba's multimodal, vision-capable agent model released in June 2026. It's the counterpart to the text-only Qwen3.7-Max, built on the same language backbone with added vision understanding and GUI grounding, and designed for screen perception, browser automation, GUI navigation, and hybrid GUI+CLI agentic workflows. It supports a 1M-token context, up to 65,536 output tokens, and an internal chain-of-thought reasoning budget up to 256,000 tokens; it reaches 79.0 on ScreenSpot Pro and 70.3 on Terminal-Bench. Velokey provides an affordable, easy-to-integrate Qwen3.7-Plus API: a unified chat endpoint, a clear request flow, and below-list pricing for production systems, agent pipelines, and automation tools.

Multimodal screen perception & GUI grounding

Adds vision on top of the language backbone to read computer screens and UIs, precisely grounding buttons, panels, and other elements. Reaches 79.0 on ScreenSpot Pro, laying the base for interface understanding and operation.

View Documentation →
Multimodal screen perception & GUI grounding

GUI navigation & browser automation

Designed for browser automation, GUI navigation, and hybrid GUI+CLI agentic workflows, operating continuously across windows, pages, and terminals. Reaches 70.3 on Terminal-Bench.

View Documentation →
GUI navigation & browser automation

1M-token context & preserve_thinking

Supports a 1M-token context and up to 65,536 output tokens, with a reasoning budget up to 256,000 tokens; preserve_thinking keeps reasoning state across tool calls instead of resetting the chain of thought each call.

View Documentation →
1M-token context & preserve_thinking

Low-cost multimodal agent

Official pricing of $0.4 input / $1.6 output per million tokens, with cached input even cheaper — significantly below Qwen3.7-Max, fit for large-scale agent deployments.

View Documentation →
Low-cost multimodal agent

How to deploy the Qwen3.7-Plus API on Velokey

Get started with just a few steps.

1

Sign up and get an API Key

Sign in to the Velokey console to generate an API Key that authenticates every request sent to Qwen3.7-Plus.

2

Configure request parameters

Set model to qwen-3-7-plus and submit messages with visual inputs like screenshots; enable preserve_thinking in the agent loop to keep reasoning state across tool calls.

3

Integrate and start calling

Send requests to Velokey's unified /v1/chat/completions endpoint to power GUI agents, browser automation, and RPA flows, with usage managed in one console.

Real-world use cases for Qwen3.7-Plus

From screen automation to agent development, covering many high-autonomy scenarios.

Screen perception & visual UI testing

With screen perception and GUI grounding, fit for reading interfaces, locating elements, and driving visual UI testing and regression.

Browser automation & RPA

Built for browser automation and GUI navigation — fit for multi-step RPA across web and desktop apps.

Hybrid GUI+CLI agents

Supports hybrid GUI and command-line agentic workflows, staying stable on long tasks with preserve_thinking.

Desktop app & file operation automation

Perceives and operates desktop app interfaces — fit for cross-window file management and multi-step desktop automation.

Data entry & dashboard automation

Reads spreadsheets and dashboard UIs and grounds controls precisely — fit for data entry, scraping, and ops dashboard automation.

Large-scale low-cost agents

With low input/output pricing and cached-input discounts, fit for high-volume, at-scale agent deployments.

Why choose Velokey for Qwen3.7-Plus

Discount on list price

Call Qwen3.7-Plus at a lower price on Velokey — pay-as-you-go with no forced subscription, reducing upfront cost.

Unified API interface

One API Key accesses Qwen3.7-Plus and other models — no juggling multiple accounts and keys, simplifying integration.

Complete docs and migration guidance

Endpoint references, parameter details, and visual-input examples help you adopt screen perception and GUI automation quickly.

Stable and highly available

Automatic failover and stable fallback routes maintain availability when the primary route is down, keeping production reliable.

API Reference

Complete API call examples and parameter descriptions

Endpoint

https://api.velokey.ai/v1/chat/completions

Authentication

Bearer YOUR_API_KEY

Request Example

curl https://api.velokey.ai/v1/chat/completions \
  -X POST \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.7-plus",
    "messages": [{"role": "user", "content": "Hello!"}],
    "temperature": 0.7
  }'

Response Example

{
  "id": "req_abc123",
  "model": "qwen3.7-plus",
  "created": 1234567890,
  "data": { ... }
}

Qwen3.7-Plus API FAQ

How does Qwen3.7-Plus differ from Qwen3.7-Max?

Qwen3.7-Plus is the multimodal, vision-capable counterpart to the text-only Qwen3.7-Max, built on the same language backbone with added vision understanding and GUI grounding. It targets screen perception, browser automation, and GUI navigation, whereas Qwen3.7-Max is text-only.

What does the preserve_thinking parameter do?

preserve_thinking maintains the model's reasoning state across multiple tool calls in an agent loop, so the chain of thought isn't reset on each tool call — keeping long-horizon tasks coherent and reducing redundant re-thinking.

What are the context and output limits?

Qwen3.7-Plus supports a 1M-token context window and up to 65,536 output tokens, with an internal chain-of-thought reasoning budget up to 256,000 tokens.

How does it perform on benchmarks?

At launch, Qwen3.7-Plus reaches 79.0 on ScreenSpot Pro and 70.3 on Terminal-Bench, reflecting its screen-grounding and terminal-agent capabilities.

How is it billed on Velokey?

Official pricing is $0.4 input / $1.6 output per million tokens, with cached input even cheaper — significantly below Qwen3.7-Max. This page's pricing area shows the current Velokey price with a discount on list price.

Start building with Qwen3.7 Plus today

Use one API key to access low-cost, stable AI models through Velokey.

Get API KeyView Docs