Qwen4 Max

byQwen
Official docs

Qwen4 Max is a reasoning model from Qwen released on Nov 16, 2026. It reads text, images and video and writes text, with a 984K token context window and up to 262K tokens per reply.

Show more

It costs $1.50 per million input tokens and $4.50 per million output tokens. Cached input bills at $0.075, 95% less than fresh input.

It supports tool calling, structured JSON output and prompt caching.

12 providers serve it, including Deep Infra, Novita AI and Vercel AI Gateway. The lowest input price is $1.41 per million tokens at Deep Infra.

Modalities
In / out price
$1.50 / $4.50 per 1M
Context
984K
Max output
262K
Released
Nov 16, 2026
Knowledge cutoff
n/a
  • Tool calling
  • Structured output
  • Reasoning
  • Prompt caching
  • Open weights
  • Free to use

Qwen4 Max pricing

USD, as listed on Nov 17, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.

Input$1.50 / 1M tokens
Output$4.50 / 1M tokens
Cached input (read)$0.075 / 1M tokens

Qwen4 Max providers

12 providers serve it, including Deep Infra, Novita AI and Vercel AI Gateway. The lowest input price is $1.41 per million tokens at Deep Infra. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.

ProviderInput /MOutput /MCache read /MContextMax output
Deep Infra$1.41$4.24$0.0711M262K
Novita AI$1.41$4.24$0.0711M131K
Vercel AI Gateway$1.50$4.50$0.0751M384K
NanoGPT$1.41$4.24$0.0711M131K
Kilo Gateway$1.43$4.28$0.07121M131K
Charm Hyper$1.50$4.50$0.0751M128K
DevPass (LLM Gateway)$1.50$4.50$0.075984K262K
Eden AI$1.50$4.50$0.0751M262K
EmpirioLabs AI$1.50$4.50$0.075984K262K
LLM Gateway$1.50$4.50$0.075984K131K
Venice AI$1.50$4.50$0.0751M393K
CrossModel$1.60$4.80$0.081M393K

What Qwen4 Max costs per month

Pick a workload close to yours or type your own volumes.

Qwen4 Max per month
$95.63
Without caching
$160
Per request
$0.0032

Supported request parameters

What you can set when you call Qwen4 Max through an OpenAI compatible API.

  • Toolstools
  • Structured outputsstructured_outputs
  • Reasoningreasoning
  • Temperaturetemperature

Alternatives to Qwen4 Max

Models that take the same inputs and call tools, closest in price, cheaper ones first.

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 15 providers.

    by metaSep 2, 20261.05M context$1.25/M input tokens$4.25/M output tokens15 providers

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 16 providers.

    by metaAug 5, 2026$1.25/M input tokens$4.25/M output tokens16 providers

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 40 providers.

    by googleSep 2, 20261.05M context$0.75/M input tokens$3.75/M output tokens40 providers

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 27 providers.

    by googleJul 21, 2026$0.75/M input tokens$3.75/M output tokens27 providers

  • Reads text, images, audio and video. Tool calling, structured output, reasoning. Served by 21 providers.

    by metaOct 15, 2026$1.25/M input tokens$4.25/M output tokens21 providers

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning.

    by googleJul 30, 2026$1/M input tokens$5/M output tokens

More from Qwen

  • Reads text and images. Tool calling, structured output, reasoning.

    by qwenOct 29, 2026$0.04/M input tokens$1.35/M output tokens

  • Reads text and images. Tool calling, reasoning.

    by qwenOct 17, 2026$0.30/M input tokens$1.20/M output tokens

  • Reads text and images. Tool calling, reasoning.

    by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens

  • Reads text and images. Tool calling, reasoning.

    by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens

  • Reads text and images. Tool calling, reasoning.

    by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens

  • Reads text and images. Tool calling, reasoning.

    by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens

All Qwen models

Qwen4 Max questions

How much does the Qwen4 Max API cost?

$1.50 per million input tokens and $4.50 per million output tokens, with cached input at $0.075. The estimator on this page turns that into a monthly bill for your own workload.

What is the context window of Qwen4 Max?

983,616 tokens of input, and it can write up to 262,144 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.

Which providers serve Qwen4 Max?

12 providers serve it, including Deep Infra, Novita AI and Vercel AI Gateway. The lowest input price is $1.41 per million tokens at Deep Infra. Prices differ by host, so the Providers table on this page lists each one with its input and output price.

Does Qwen4 Max support tool calling?

Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.

Is Qwen4 Max open source?

No. Qwen serves it through an API only, so you cannot download the weights or host it yourself.

When was Qwen4 Max released?

Nov 16, 2026.

Catalog data from models.dev (MIT licensed), refreshed daily, last on Nov 17, 2026. The summary is written from these facts.