Qwen3 Max

alibaba/qwen3-max

Maker: Alibaba (Qwen), China
Released: 2025-09-23
Knowledge cutoff: 2025-04
Family: qwen
Weights: closed
Tasks: text.chat
Cheapest offering: Alibaba Cloud Model Studio (DashScope), about $0.003 for a typical text.chat call

Try it in the sandbox Use it from the API

Offerings

Provider	Model id at the provider	Status	Price per 1M tokens	Per-unit prices	Limits	Capabilities (level)
Alibaba Cloud Model Studio (DashScope)	`qwen3-max`	deprecated	Input: $1.2 Output: $6 Since 2026-11-04 · models.dev, MIT	none	Context: 262,144 tokens Max output: 65,536 tokens	`input.text` claimed `output.text` claimed `tools` claimed `tool_choice` claimed `reasoning` claimed
DeepInfra	`Qwen/Qwen3-Max`	deprecated	Input: $1.2 Output: $6 Cache read: $0.24 Input, prompts over 32,000 tokens: $2.4 Output, prompts over 32,000 tokens: $12 Cache read, prompts over 32,000 tokens: $0.48 Input, prompts over 128,000 tokens: $3 Output, prompts over 128,000 tokens: $15 Cache read, prompts over 128,000 tokens: $0.6 Since 2026-11-03 · models.dev, MIT	none	Context: 256,000 tokens Max output: 65,536 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `tool_choice` claimed `prompt_caching` claimed

Quality scores

Basis	Score (0–1)	Raw	Measured	Source
`epoch:gpqa_diamond`	0.753	0.7260	2025-10-06	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`epoch:frontiermath`	0.202	0.1895	2026-08-30	Epoch AI, CC-BY-4.0, normalized by Nanner Tech

Aliases

Other names the API accepts for this model.

alibaba-cn/qwen3-max
qwen/qwen3-max
qwen3-max

Use it from the API

Look this model up, or ask for the best model for its task on the providers that offer it. See the quickstart and the API reference.

Look up this model

curl 'https://rhumbdata.com/v1/models/alibaba/qwen3-max' \
  -H "Authorization: Bearer $RHUMB_KEY"

Resolve text.chat on its providers

curl 'https://rhumbdata.com/v1/resolve?task=text.chat&providers=dashscope,deepinfra' \
  -H "Authorization: Bearer $RHUMB_KEY"

Built from catalog version 2026-11-04.3 of 2026-11-04. Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).