Qwen

Qwen3-Max

Qwen3's largest model, with a non-thinking chat mode and a dedicated thinking mode for hard reasoning.

ActiveReleased September 24, 2025
Tool callingCan invoke external tools and APIs (function calling) mid-response.Structured outputCan return JSON or schema-constrained responses instead of free text.ReasoningUses extended thinking / chain-of-thought for harder multi-step problems.Effort controlLets you dial thinking depth (low / medium / high) to trade cost for quality.Fine-tuningSupports training a custom variant on your own data.

Source: Qwen (Alibaba Model Studio) pricing, Qwen models

Price per 1M tokens via Alibaba (OpenRouter)
$0.78 in / $3.9 out
Context window262,144
Max output32,768
Cache read$0.156 / M
ModalitiesText → Text

Pricing

Every billing leg from the live catalog, in USD per 1M tokens.

Billing legRate
Input$0.78 / M
Output$3.9 / M
Cache read$0.156 / M

Cost calculator

Billing-grade math over the rate card above, including the thinking tokens most estimates miss.

Hidden reasoning tokens bill as output. 1.0x = thinking off. Medium-effort reasoning typically lands near 3x; heavy reasoning runs 6x to 8x. Set it to match your workload.

Estimated monthly cost
$390
at current list prices
Fresh input$156
Cached input$0.00
Output incl. thinking$234
Track this automatically →

Provider

Where this model runs, and what it charges.

PlatformInput / MOutput / MCache read / MBatchAccess
Alibaba
$0.78$3.9$0.156—via OpenRouter

Price history

Has this model gotten cheaper or more expensive?

No changePriced at $0.78 / $3.9 per 1M since July 10, 2026.

More from Qwen

Other models from the same provider.

Qwen3.7-Max
qwen/qwen3.7-max
$1.25 / $3.75 in / out per 1M
Qwen3.7-Plus
qwen/qwen3.7-plus
$0.32 / $1.28 in / out per 1M
Qwen3.6-Max
qwen/qwen3.6-max
$1.04 / $6.24 in / out per 1M
Qwen3.6-Plus
qwen/qwen3.6-plus
$0.325 / $1.95 in / out per 1M
Qwen3.6-Flash
qwen/qwen3.6-flash
$0.1875 / $1.13 in / out per 1M
Qwen3.5-Plus
qwen/qwen3.5-plus
$0.3 / $1.8 in / out per 1M

Stop estimating. Track it.

SuperPenguin meters every Qwen3-Max call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.

Get started free

Rates are generated from SuperPenguin's live pricing catalog.