OpenRouter 模型 ↗ · 2026-11-16
qwen/qwen4-max
Model release OpenRouter 模型 Source language: Chinese
OpenRouter listed the model on 2026-11-16 (listing date does not equal the model's official release date); context: 1,000,000 tokens; input price: $1.5000 per million tokens; output price: $4.5000 per million tokens; positioning (source description): Qwen4 Max is the flagship model in Alibaba's Qwen4 series.
Full text
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.