Qwen 4 Max
Summary
Qwen 4 Max is a proprietary language model from Alibaba (Qwen), released on 16 Nov 2026. It accepts text and images and generates text, with a 1M-token context window and up to 384K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $1.41 per million input tokens and $4.24 per million output tokens (DeepInfra), across 4 providers we track.
Flagship multimodal model for coding, office productivity, frontend design, and complex agentic tasks
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Alibaba (Qwen) |
|---|---|
| Release date | 16 Nov 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Proprietary (API only) [models.dev] |
| Context window | 1M (1,000,000 tokens) [models.dev] |
| Max output | 384K tokens [models.dev] |
| Input | Text and images [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
Qwen 4 Max API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| DeepInfra Qwen/Qwen4-Max | $1.41 | $4.24 | $0.07 | 1M | models.dev, 18 Nov 2026 |
| Novita AI qwen/qwen4-max | $1.41 | $4.24 | $0.07 | 1M | models.dev, 18 Nov 2026 |
| OpenRouter qwen/qwen4-max | $1.43 | $4.28 | $0.07 | 1M | OpenRouter, 18 Nov 2026 |
| Vercel AI Gateway alibaba/qwen4-max | $1.50 | $4.50 | $0.07 | 1M | models.dev, 18 Nov 2026 |
Frequently asked questions
What is the context window of Qwen 4 Max?
Qwen 4 Max has a context window of 1,000,000 tokens (1M) and can generate up to 384,000 tokens in a single response, according to models.dev.
How much does the Qwen 4 Max API cost?
Qwen 4 Max is listed from $1.41 per million input tokens and $4.24 per million output tokens (DeepInfra). Prices last verified 18 Nov 2026.
Is Qwen 4 Max open source?
No. Qwen 4 Max is a proprietary model; Alibaba (Qwen) has not released its weights. It is available through APIs including DeepInfra, Novita AI, OpenRouter, Vercel AI Gateway.
When was Qwen 4 Max released?
Alibaba (Qwen) released Qwen 4 Max on 16 Nov 2026, according to models.dev.
Which providers offer Qwen 4 Max?
We track Qwen 4 Max on 4 providers: DeepInfra, Novita AI, OpenRouter, Vercel AI Gateway.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| ERNIE-Light-DT-1.0 | Baidu | 10 Nov 2026 | 1M | $1.13 | $3.94 | – |
| GPT-6.1 Terra | OpenAI | 26 Oct 2026 | 1.1M | $1 | $5 | Closed |
| GPT-6.1 Terra Pro | OpenAI | 26 Oct 2026 | 1.1M | $1 | $5 | – |
| Gemini 4 Hydrogen | Google DeepMind | 12 Nov 2026 | 1M | $1.50 | $7.50 | Closed |
| GLM 5.3 Prime | Zhipu AI (Z.ai) | 23 Sept 2026 | 1M | $1.68 | $5.28 | – |
| Muse Spark 1.3 Contributor | Meta | 2 Sept 2026 | 1M | $1.25 | $4.25 | Closed |
Change history
- OpenRouter price changed: input $1.50 → $1.43, output $4.50 → $4.28 per 1M tokens
- Now listed on Novita AI
- Now listed on DeepInfra
- Max output changed from 131K to 384K
- Name changed from Qwen4 Max to Qwen 4 Max
- Input modalities changed from text, image, video to text, image
- Now listed on OpenRouter
- Added to the directory
- Now listed on Vercel AI Gateway
Sources
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/alibaba/qwen4-max.toml
- https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/qwen/qwen4-max.toml
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen4-Max.toml
- https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/qwen/qwen4-max.toml
- https://openrouter.ai/qwen/qwen4-max