NezhaGateNezhaGate
简体中文English ✓Español한국어日本語
Log in Get API Key
Chat

Qwen3.7 Max

⧉
qwen3.7-max

Qwen3.7 Max is the flagship of Alibaba Cloud's Qwen 3.7 generation, strong at reasoning, coding and agent work, with dependable Chinese and English. It always thinks before it answers, with the reasoning in reasoning_content, and it supports tool calling, streaming and prompt caching. Fully OpenAI-compatible: set model to qwen3.7-max. Pay-as-you-go, failed calls never billed.

ChatReasoningCodingTool callingOpenAI compatible
Get API Key → API Docs

Live Test · Playground

Try out Qwen3.7 Max right here (available after login).

Input

Advanced
Web search
Memory · multi-turn

Conversation

Start a conversationType a message below to begin

About Qwen3.7 Max

Qwen3.7 Max is the flagship of Alibaba Cloud's Qwen 3.7 generation, served on NezhaGate through the OpenAI-compatible API. It is strong at reasoning, coding and agent work, with dependable Chinese and English. It always thinks before it answers: the reasoning comes back in message.reasoning_content and the answer in content, so clients that only read content need no changes. Tool calling, streaming and prompt caching are supported (a repeated long prefix settles at the cache rate). Set model to qwen3.7-max; pay-as-you-go, failed calls never billed.

Use cases

Complex reasoning and maths

It thinks before it answers, which suits multi-step reasoning, maths and logic problems.

Code generation and review

Writing, refactoring, explaining and reviewing code, with structured output.

Agents and tool calling

OpenAI-format tools / tool_calls plug into any agent framework.

Q&A over long documents

We verified it pinpoints facts inside documents of more than 100K tokens, and repeated questions about the same document hit the cache and cost less.

How to choose

Choose Qwen3.7 Max when you need strong reasoning and coding. For long documents and multi-document analysis, compare it with Kimi K3; when cost matters most, choose DeepSeek V4.1 Flash. Switching is just the model field.

FAQ

Can I turn thinking off or limit its length?
No. Through NezhaGate, Qwen3.7 Max always thinks, and parameters such as reasoning_effort, enable_thinking or thinking_budget do not change how long it reasons. Reasoning tokens are billed at the output rate inside usage.completion_tokens.
Can max_tokens cap my spend?
max_tokens does not cap the reasoning part: even with a very small value the model may think for thousands of tokens first, and you are billed for the actual tokens in usage. To keep costs down, ask for short answers in the prompt.
Is prompt caching supported?
Yes. A repeated long prefix hits the cache and that part settles at the cache rate; we measured a second question about the same long document costing about a fifth of the first.
Does it support tool calling and streaming?
Yes to both. tools / tool_calls use the OpenAI format; with stream=true the reply arrives as SSE chunks and the reasoning streams in delta.reasoning_content.
Am I charged for failed calls?
No. Only calls that return normally are settled, at actual usage; upstream errors and timeouts never touch your balance.

Related Models

Explore other models you can integrate.

View all →
Kimi K3 Chat

Kimi K3

kimi-k3

Moonshot's new flagship - long context and agents

$1.80/1M in · $9.00/1M out ↓40% View →
Grok 4.7 Chat

Grok 4.7

grok-4.7

xAI's flagship reasoning model - long context

$0.30/1M in · $0.90/1M out ↓85% View →
GLM-5.3 Chat

GLM-5.3

glm-5.3

The new Z.ai flagship - coding and agents

$0.34/1M in · $1.25/1M out ↓73% View →
DeepSeek V4.1 Flash Chat

DeepSeek V4.1 Flash

deepseek-v4.1-flash

DeepSeek's current Flash model - thinking on or off

$0.09/1M in · $0.36/1M out ↓40% View →
GPT-6 Sol Chat

GPT-6 Sol

gpt-6-sol

Built for complex coding and agentic workflows - 1.05M context

$0.20/1M in · $1.00/1M out ↓90% View →
Gemini 3.1 Pro Chat

Gemini 3.1 Pro

gemini-3.1-pro

Next-generation flagship reasoning model from Google

$0.50/1M in · $3.00/1M out ↓75% View →