Skip to content
AI Dev Toolkit.
Esc
  • Loading…

Qwen · Model

Qwen4 Max API pricing, cost and context window

Qwen4 Max costs $1.425 per million input tokens and $4.275 per million output tokens. Cached input costs $0.0713. It reads up to 1,000,000 tokens and writes up to 131,072 per reply. Prices checked 2026-11-22. By blended price it is number 10 of Qwen’s 12 current models here, counting from the cheapest.

Input / 1M
$1.425
Output / 1M
$4.275
Cached / 1M
$0.0713
Context
1,000,000
Max output
131,072
Released
2026-11-16

Estimate your cost with Qwen4 MaxCompare all Qwen modelsCount tokens for Qwen4 Max

Pricing

How much does Qwen4 Max cost per million tokens?

Price per 1M tokensInputOutput
Standard$1.425$4.275
Cached input (read)$0.0713–
Cache write$1.7813–

Output costs 3.0× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 5% of the normal input price.

Work out your monthly Qwen4 Max bill in the cost calculatorSee what prompt caching saves

History

Has Qwen4 Max’s price changed?

  1. Price cut, −5.0% blended

    Input
    from $1.50 to $1.425
    −5.0%
    Output
    from $4.50 to $4.275
    −5.0%
    Cached input
    from $0.075 to $0.0713
    −5.0%
    Cache write
    from $1.875 to $1.7813
    −5.0%

Every change across all models is in the AI pricing changes log.

Examples

How much does a typical Qwen4 Max request cost?

WorkloadTokens in / outRequests/dayPer requestPer month
Support chatbot50% cached1,500 / 4001,000$0.00283$86.15
RAG app20% cached6,000 / 500500$0.00906$137.83
Coding agent80% cached40,000 / 2,000200$0.0222$135.23
Document summariser8,000 / 600300$0.014$127.43

Change any number in the cost calculator.

Context

What is Qwen4 Max’s context window and max output?

Qwen4 Max accepts up to 1,000,000 tokens per request, roughly 750,000 English words or 1,500 pages. That budget is shared between your prompt and the reply, and a single reply is capped at 131,072 tokens.

Filling the whole window with one prompt costs about $1.43 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.

Check whether your text fits Qwen4 Max’s window.

Features

What can Qwen4 Max do?

Image input
Yes
Tool / function calling
Yes
Reasoning mode
Yes
Prompt caching
Yes
Structured output
Yes
Open weights
No
Accepts
text, image, video
Knowledge cutoff
Not published

As declared by the provider’s API. It shows a feature exists, not how well it works.

API

What is the Qwen4 Max API model ID?

OpenRouter
qwen/qwen4-max

Use the OpenRouter ID when calling it through OpenRouter; Qwen’s own API may name it differently. See the model ID reference for the providers we document.

Qwen

Where does Qwen4 Max sit in Qwen’s line-up?

Ranked by blended price (three parts input to one part output, $2.1375 per 1M for Qwen4 Max), it is number 10 of Qwen’s 12 current models here, counting from the cheapest. One step down, Qwen3.5 397B A17B costs $1.0875 blended (49% less). Unlike Qwen4 Max, it reads up to 262,144 tokens (1,000,000 here), caps a reply at 81,920 tokens (131,072 here) and has open weights. One step up, Qwen3.8 2.4T A95B costs $3 (1.4× as much). Unlike Qwen4 Max, it doesn’t accept images or video, reads up to 262,144 tokens (1,000,000 here) and caps a reply at 65,536 tokens (131,072 here). See every Qwen model and price

ModelInput / 1MOutput / 1MContextReleased
Qwen3.5-9B$0.17$0.25262,1442026-03-10
Qwen3.8 Flash$0.15$0.471,000,0002026-08-26
Qwen3.8 Omni Flash$0.15$0.471,000,0002026-09-21
Qwen3 Coder Next$0.12$0.80262,1442026-02-04
Qwen3.6 35B A3B$0.10$0.90262,1442026-04-27
Qwen3.7 Plus$0.32$1.281,000,0002026-06-03
Qwen3.8 27B$0.15$1.875262,1442026-08-14
Qwen3.5-122B-A10B$0.26$2.08262,1442026-02-25
Qwen3.5 397B A17B$0.45$3262,1442026-02-16
Qwen4 Max (this page)$1.425$4.2751,000,0002026-11-16
Qwen3.8 2.4T A95B$2$6262,1442026-08-12
Qwen3.8 Max Prime$4$121,000,0002026-09-23

Qwen’s current models with a page here, cheapest first. Older and superseded models are listed on the provider page and in the comparison table.

History

Is Qwen4 Max cheaper than Qwen3.8 Max (0902)?

The previous model in this line is Qwen3.8 Max (0902), first listed on 2026-09-03. Compared with it, Qwen4 Max’s input price is 29% lower and its output price is 29% lower.

ModelInput / 1MOutput / 1MContextReleased
Qwen3.8 Max (0902)$2$61,000,0002026-09-03
Qwen3.7 Max$1.475$4.4251,000,0002026-05-21

Earlier releases with the same name and size in our data, newest first. Dates are when our source first listed each model.

Save

What are cheaper alternatives to Qwen4 Max?

Current models from major providers, one per provider, that keep image input, tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.

Compare

Which models cost about the same?

Current models from other major providers, closest blended price.

FAQ

Qwen4 Max questions

How much does Qwen4 Max cost?

Qwen4 Max costs $1.425 per million input tokens and $4.275 per million output tokens, with cached input at $0.0713. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.00385. Use the LLM cost calculator for your own workload.

What is Qwen4 Max’s context window?

1,000,000 tokens, about 750,000 English words or 1,500 printed pages, shared between your prompt and the reply. A single reply can be up to 131,072 tokens.

Does Qwen4 Max support prompt caching and batch requests?

Yes, cached input is billed at $0.0713 per million tokens (5% of the normal input price), and writing a prompt to the cache costs $1.7813 per million tokens. No batch price is published for it.

What are cheaper alternatives to Qwen4 Max?

With the same essentials (image input and tool calling), the cheapest options are Qwen3.8 Omni Flash (89% cheaper), MiniMax M3.1 Flash (88% cheaper), GLM 4.6V (79% cheaper). Cheaper doesn’t mean equivalent, so test them on your own prompts.

What is the API model ID for Qwen4 Max?

On OpenRouter it is qwen/qwen4-max. Qwen’s own API may use a different name, so check its model list before you deploy. Pass the ID as the model value in each request.

When was Qwen4 Max released?

Qwen4 Max was first listed on 2026-11-16. It follows Qwen3.8 Max (0902), first listed on 2026-09-03. Release dates here are when our price source first listed each model.

Is Qwen4 Max cheaper than Qwen3.8 Max (0902)?

The previous Qwen model in the same line is Qwen3.8 Max (0902), first listed on 2026-09-03. Compared with it, Qwen4 Max’s input price is 29% lower and its output price is 29% lower. Prices are only part of the picture, so test the newer model on your own prompts before switching.

Is Qwen4 Max open source?

No, Qwen4 Max is only available through Qwen’s API and partners; its weights aren’t published.

Prices checked · Page updated

Sources: OpenRouter models API and LiteLLM model prices and context windows, checked daily; open-weight prices are typical hosted prices. Confirm critical numbers on Qwen’s pricing page. Every price move is in the AI pricing changes log. See our methodology.

Keep exploring