Qwen 3.7 Max
Qwen 3.7 Max is Alibaba Cloud's flagship agent-tuned model in the Qwen 3.7 line, with a context window of 991K tokens and an emphasis on long-horizon tool use, multi-file coding, and office workflow automation. Your use is subject to Alibaba Cloud's Terms & Privacy Policies.
View API reference- Input and output price
- Input $2.50, Output $7.50, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'alibaba/qwen3.7-max', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Qwen 3.7 Max by Alibaba Cloud. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Qwen 3.7 Max
Qwen 3.7 Max
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Qwen 3.7 Max through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.7-max', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Qwen 3.7 Max request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.7-max', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. alibaba/qwen3.7-max. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Qwen 3.7 Max supports up to 64,000 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 991K-token context window |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK alibaba provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.7-max', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['alibaba'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.7-max', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3.7-max', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingMore models by Alibaba Cloud
| Model |
|---|
| 991K | 1.2 s | 61 tps | $2/M | $6/M | Read$0.25/M Write$2.50/M | — | +2 | | 09/01/2026 | |||||
| 991K | 2.9 s | 62 tps | $0.16/M | $0.47/M | Read$0.02/M Write$0.20/M | — | +2 | | 08/26/2026 | |||||
| 1M | 0.5 s | 372 tps | $0.10/M | $0.40/M | Read$0.01/M Write$0.63/M | — | +1 |   +4 | 08/14/2026 | |||||
| 1M | 0.6 s | 101 tps | $2/M | $6/M | Read$0.25/M Write$2.50/M | — | +1 |  | 08/02/2026 | |||||
| 991K | 2.4 s | 102 tps | $0.03/M+2 more | $0.13/M+2 more | Read$0.006/M Write$0.04/M | — | +2 | | 07/28/2026 | |||||
| 1M | 2.2 s | 77 tps | $0.40/M+1 more | $1.60/M+1 more | Read$0.08/M Write$0.50/M | — | +2 | | 06/02/2026 |
Copy link to headingAbout Qwen 3.7 Max
Qwen 3.7 Max is the Max-tier release in the Qwen 3.7 generation, succeeding Qwen3.6-Max-Preview in Alibaba Cloud's closed-weight API line. The model is served through Alibaba Cloud with a context window of 991K tokens, which suits full-repository ingestion, long agent traces, and multi-document analysis without segmentation.
Alibaba Cloud describes Qwen 3.7 Max as designed as an agent foundation. The model targets coding agents that plan and act across many turns, office and productivity tasks that route work through multi-agent orchestration, and long-horizon autonomous execution where the model must maintain coherent reasoning across hundreds of sequential tool calls. Reported improvements over Qwen3.6-Max-Preview concentrate in frontend prototyping and complex multi-file engineering work.
Like other Max-tier entries, Qwen 3.7 Max supports tool calling and structured outputs, with extended-thinking mode available for high-difficulty reasoning, scientific computation, and expert-level queries. The thinking budget can be tuned per request to balance depth of reasoning against latency and token spend. Qwen 3.7 Max is text-only; for vision input, the sibling Qwen3.7-Plus is the multimodal entry in the 3.7 lineup.
You can integrate Qwen 3.7 Max through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Agent workflows that chain hundreds of tool calls produce high output-token volume. Use the AI Gateway cost dashboard to monitor per-session spend and tune the thinking budget before running production traffic at scale.
- Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use Qwen 3.7 Max
Best for
- Long-Horizon Coding Agents: Sustained tool-calling sessions across many turns with planning, retries, and dead-end recovery
- Multi-File Software Engineering: Refactoring, diff editing, and frontend prototyping across a repository
- Office Workflow Automation: Routing productivity tasks through multi-agent orchestration
- Expert Reasoning Tasks: Scientific computation, mathematics, and structured analysis with extended-thinking mode
- Repository Ingestion: Long-context workloads using the window of 991K tokens for full codebases and tool traces
Consider alternatives when
- Vision Or Multimodal Input: Qwen3.7-Plus is the multimodal entry in the 3.7 line when image inputs are needed
- Latency-Sensitive Pipelines: A Plus or Flash-tier model serves users better when extended-thinking traces add unnecessary overhead
- Strict Token Budgets: A smaller model is a closer fit when per-session spend on a flagship Max model isn't justified
- Built-In Autonomous Search: Qwen3-Max-Thinking is a stronger fit when integrated search and code interpreter tools are required
Copy link to headingConclusion
Qwen 3.7 Max extends the Qwen Max tier with an agent-first design that targets long-horizon tool use, multi-file coding, and office workflow automation. Routing through AI Gateway gives you a single integration surface, provider failover, and consolidated billing while you build against the latest generation in the Max line.
Copy link to headingFrequently Asked Questions
What is the relationship between Qwen 3.7 Max and Qwen3.6-Max-Preview?
Qwen 3.7 Max is the Max-tier flagship in the Qwen 3.7 generation, succeeding Qwen3.6-Max-Preview. Alibaba Cloud positions Qwen 3.7 Max as an agent foundation with improvements in long-horizon tool use, multi-file coding, and office workflow automation.
What is the context window for Qwen 3.7 Max?
The context window is 991K tokens. This supports full-repository ingestion, long agent traces with hundreds of sequential tool calls, and multi-document analysis without segmentation.
Can Qwen 3.7 Max accept image or file inputs?
Qwen 3.7 Max is text-only. For vision input within the 3.7 line, use Qwen3.7-Plus, which is the multimodal entry in the generation.
Does Qwen 3.7 Max support tool calling?
Yes. Qwen 3.7 Max supports structured tool calling and is tuned for agent workflows that chain many sequential tool invocations across long-horizon sessions.
How does extended-thinking mode work on Qwen 3.7 Max?
Extended-thinking mode generates an internal reasoning trace before producing the final answer, which improves accuracy on high-difficulty logical reasoning, scientific computation, and expert-level queries. The thinking budget is tunable per request to balance depth against latency and token spend.
How do I access Qwen 3.7 Max through AI Gateway?
Authenticate with an AI Gateway API key or OIDC token and reference `
alibaba/qwen3.7-max` as the model. You can call Qwen 3.7 Max through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python.Does Qwen 3.7 Max support zero data retention?
Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.
Where can I see live latency and cost data for Qwen 3.7 Max?
This page shows live throughput, time-to-first-token, and pricing metrics for Qwen 3.7 Max measured across real AI Gateway traffic.