Skip to content
Alibaba Qwen

Qwen3 Max

qwen/qwen3-max
Language

Alibaba's closed flagship: broad knowledge, strong multilingual output and vision input at mid-tier pricing.

Model overview

Context window

256K

tokens

Input price

—

quoted on request

Output price

—

quoted on request

Weekly volume

—

tokens / week

Open weights

No

API only

Capabilities

5

of 11 tags

Description

Qwen3 Max is a language model from Alibaba Qwen. Webparam does not stock this model yet and can source it on request — tell us what you need it for and we will come back with availability and a price. Alibaba Qwen’s stated focus is the broadest open model family in the world. The weights are not published, so it is API-only.

Capabilities

Tool calling
Calls functions you define and returns their arguments as structured data, the basis of agents.
JSON mode
Constrains the response to valid JSON matching a schema you supply.
Streaming
Emits tokens as they are generated, so answers appear progressively rather than all at once.
Vision input
Accepts images alongside text in the prompt.
Caching
Reuses already-processed prompt prefixes across requests, cutting input cost for repeated context.

Strengths & weaknesses

Strengths

  • Excellent multilingual quality
  • Vision input included
  • Strong all-round benchmark profile

Weaknesses

  • Closed weights unlike the rest of the family
  • Output pricing above open peers

Pricing

Pricing for Qwen3 Max, per 1M tokens
RatePriceUnit
Input— quoted on request—
Output— quoted on request—

Prompt caching is supported, so repeated prefixes bill below the listed input rate. This model is not provisioned yet; the rate is quoted on request.

Context window

256Ktokens

covers prompt and response together, so a long input leaves less room for the answer.

256K tokens against a peer range of 32K to 10M, median 256K. Compared across 34 language models. Logarithmic scale.

Supported features

Feature support for Qwen3 Max
FeatureSupport
Tool callingSupported
JSON modeSupported
StreamingSupported
Vision inputSupported
Audio inputNot supported
Long contextNot supported
Open weightsNot supported
ReasoningNot supported
Fine-tunableNot supported
BatchNot supported
CachingSupported

Example use cases

  • Multilingual products

  • Document understanding

  • General assistants

Related models

Comparison

Compare against anything →
Qwen3 Max compared with Qwen3 235B A22B Instruct 2507 and GPT-5.1
AttributeQwen3 MaxQwen3 235B A22B Instruct 2507GPT-5.1
Context window256K256K400K
Input priceR0.00R0.00R0.00
Output price— not charged— not charged— not charged
Tool callingSupportedSupportedSupported
JSON modeSupportedSupportedSupported
Vision inputSupportedNot supportedSupported
Open weightsNot supportedSupportedNot supported
Prompt cachingSupportedNot supportedSupported

Best value in each row is highlighted. Blank cells are facts the supplier does not publish, not zeroes.

Provider information

View Alibaba Qwen →
Alibaba Qwen8 models

Alibaba Qwen · 通义千问 · Hangzhou, China · est. 2023 (Model lab; parent Alibaba founded 1999)

Alibaba's Qwen family spans every size class from edge models to frontier MoE systems, most released with open weights. Its breadth (chat, coding, vision, embeddings) and permissive licensing made it the default base model for much of the global open-source ecosystem.

Recent releases

    Documentation

    Frequently asked questions

    Input is billed at R0.00 per 1M tokens, and there is no separate output charge. Prompt caching bills repeated prefixes below the listed input rate. Every figure on this page is an illustrative placeholder.