qwen/qwen4-max

模型发布 OpenRouter 模型 原文语言:中文

OpenRouter 于 2026-11-16 将该模型列出(列出日期不等同于模型的官方发布日期);上下文长度:1,000,000 令牌;输入价格:每百万令牌 $1.5000;输出价格:每百万令牌 $4.5000;定位(来源描述):Qwen4 Max 是阿里巴巴 Qwen4 系列的旗舰模型。

全文

Qwen: Qwen4 Max

qwen/qwen4-max

Compare

Qwen4 Max is the flagship model in Alibaba's Qwen4 series. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default.

Reasoning effort can be set to low, high, or xhigh (default high), or reasoning can be turned off. Tool calling and structured outputs are supported.

Modalities

In / out price

$1.50 / $4.50per 1M

Context

1.0M

Released

Nov 16, 2026

Compare

Providers

This model is hosted by one provider. OpenRouter forwards every request without routing.

Latency / throughput

$1.50$4.50$0.075$1.875$0.0751.31s51 tok/s

100.00%

ProviderInput / Output /M

Input $1.50 / Output $4.50

51 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.4042/M tokens

Output

$4.50/M tokens

Qwen4 Max — Price history

Price history

No effective price data for this selection

$0.404$4.5077.0%100.0%

ProviderInput / Output /M

Token share

Effective in $0.404 / Effective out $4.50

Token share

100.0%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

51tok/s

P50, best across providers

Latency

1.31s

P50, best provider

Reasoning effort

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)The model was reachable. Request routed to a provider.

100.00%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

99.38%

Availability over the last 3 days

Last 72 hours

Availability 99.38%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.50%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.

omp

new

57.9Mtokens

2.

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

40.2Mtokens

3.

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

34.8Mtokens

4.

DeepSeek Harness

new

21.6Mtokens

5.

Letta

Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.

16.6Mtokens

Rest of OpenRouter

197M

Top 5 Apps

171M

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Frequently asked questions

Qwen4 Max is the flagship model in Alibaba's Qwen4 series. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default. Reasoning effort can be set to low, high, or xhigh (default high), or reasoning can be turned off. Tool calling and structured outputs are supported.

Qwen4 Max costs $1.50/M input tokens and $4.50/M output tokens, with separate rates for Cache Read at $0.075/M tokens, Cache Creation (5min) at $1.875/M tokens, and Cache Read (5min) at $0.075/M tokens.

Qwen4 Max has a 1,000,000 token context window. It supports up to 393,216 completion tokens.

Yes. Qwen4 Max accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Qwen4 Max accepts text, images, and video as input and returns text.

Qwen4 Max is served by 1 provider on OpenRouter: Alibaba Cloud Int..

Qwen3.8 Max Prime, Qwen3.8 Omni Flash, Qwen3.8 Max (0902) and 36 more are other text models from Qwen.

Qwen4 Max was released on November 16, 2026.

正文以来源语言显示。

参考来源

← 返回每日简报