Qwen · Model guide

Qwen3.7 Plus

Q: What is Qwen3.7 Plus?

Qwen3.7 Plus is available on CrossModel as qwen/qwen3.7-plus. It has a 1M-token context window and can return up to 64K tokens per request.

Q: How much does Qwen3.7 Plus cost?

Currently $ 0.29 per 1M input tokens and $ 1.13 per 1M output tokens. Cached input is billed at $ 0.029 per 1M.

Q: Does Qwen3.7 Plus support tool calling and structured output?

Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported

Q: Which endpoint do I call?

For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.

Q: Can I try it without writing code?

Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Compare

qwen/qwen3.7-plus10% off

Qwen's recommended balanced model combines a 1M-token context window, native text, image and video understanding, hybrid reasoning, function calling, structured output, caching and built-in tools.

Modalities

Context

Max output

64K

Price / 1M tokens

$ 0.32$ 0.29in$ 1.13out

StreamingTool callingJSON outputImage inputThinking mode · can be turned off

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorThe default balanced choice for coding tools, chatbots, office work and document processing.source

Best for

Enterprise knowledge work · Recommended for document processing, office productivity, data analysis and sustained conversations.(vendor claim)source
Multimodal coding agents · Its long context, vision and full tool calling suit large codebases and visual coding tasks.(vendor claim)source

Neighbouring models

qwen/qwen3.7-maxstronger —Choose Qwen3.7 Max for strongest text-only reasoning.(vendor claim)source
qwen/qwen3.7-flashfaster —Choose Qwen3.7 Flash for higher-volume, latency-sensitive workloads.(vendor claim)source

Compare them side by side →

Pricing and billing

Tiered pricing: the rate changes once the input passes the threshold.

Price / 1M tokens by input size	Input < 256.0K	Input ≥ 256.0K
Input	$ 0.32$ 0.29	$ 0.96$ 0.86
Output	$ 1.25$ 1.13	$ 3.75$ 3.38
Cache read	$ 0.032$ 0.029	$ 0.096$ 0.086
Cache write	$ 0.40$ 0.36	$ 1.20$ 1.08

Estimate a request

Input tokens10,000

Output tokens2,000

Cache hit rate0%

At this input size you are on the Input < 256.0K tier.

$ 0.0051

Estimated cost per request

10.0K × $ 0.29
+ 2.0K × $ 1.13

≈ $ 5.13 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window: 1.0M tokens
Max output: 64.0K tokens
Input / output modalities: Text + Image + Video → Text
Streaming: Supported
Tool calling: Supported
Structured output (JSON): Supported
Image input: Supported
Thinking mode: Supported· can be turned off
Available endpoints: /v1/chat/completions · /v1/responses · /v1/messages

First-party sources:Specsqwencloud.comCapabilitiesqwencloud.com 1 help.aliyun.com 2

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Agentic coding

Terminal-Bench 2.0
pass_rate·Qwen Team · 2026-06-02Terminussetup not fully disclosed
70.3%

Coding

SWE-Bench Pro
resolved_rate·Qwen Team · 2026-06-02setup not fully disclosed
57.6%
SWE-Bench Verified
resolved_rate·Qwen Team · 2026-06-02setup not fully disclosed
77.7%

Computer use

AndroidWorld
success_rate·Qwen Team · 2026-06-02setup not fully disclosed
81%
OSWorld Verified
success_rate·Qwen Team · 2026-06-02setup not fully disclosed
73.3%

Long context

MRCR v2 128K
score·Qwen Team · 2026-06-02setup not fully disclosed
91.7%

Multimodal reasoning

MMMU Pro
accuracy·Qwen Team · 2026-06-02setup not fully disclosed
79%

Scientific reasoning

GPQA Diamond
accuracy·Qwen Team · 2026-06-02setup not fully disclosed
90.3%

Tool use

MCPMark
score·Qwen Team · 2026-06-02setup not fully disclosed
58.7%

Video understanding

VideoMMMU
accuracy·Qwen Team · 2026-06-02setup not fully disclosed
85.4%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code

Anthropic's official command-line coding assistant

Cursor

AI-first code editor

Cline

Open-source AI coding agent for VS Code

Codex

OpenAI's coding agent for ChatGPT desktop and the terminal

OpenCode

Open-source terminal coding assistant

Zed

High-performance, AI-native code editor

Open WebUI

Open-source, self-hosted AI chat interface

Continue

Open-source AI coding assistant for VS Code & JetBrains

See all integration guides →

Frequently asked questions

What is Qwen3.7 Plus?

Qwen3.7 Plus is available on CrossModel as qwen/qwen3.7-plus. It has a 1M-token context window and can return up to 64K tokens per request.

How much does Qwen3.7 Plus cost?

Currently $ 0.29 per 1M input tokens and $ 1.13 per 1M output tokens. Cached input is billed at $ 0.029 per 1M.

Does Qwen3.7 Plus support tool calling and structured output?

Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported

Which endpoint do I call?

For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.

Can I try it without writing code?