Skip to content
Metered.
Qwen (Alibaba) model

Qwen3 Max Thinking

API pricing per million tokens

qwen3-max-thinking ReasoningChecked 5h ago
Cost calculator Compare
Input
$0.78
per 1M, list
Output
$3.9
per 1M tokens
Cached input
n/a
no batch tier listed
Context
262K
66K max output

Price history

$1$3Feb 15, 2026Output $3.9Input $0.78

List price since Feb 15, 2026, from Internet Archive snapshots of the OpenRouter catalog, then daily reads.

SeenModelChange
Mar 6, 2026Qwen3 Max ThinkingInput $1.2 to $0.78, Output $6 to $3.9-35%

Through a gateway

Your own numbers

100M input and 20M output tokens a month: $156.00 direct.

Related models

About Qwen3 Max Thinking

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning.

Takes text in and returns text. First listed Feb 15, 2026. Blended price $1.56 per 1M tokens at 3 input to 1 output.

OpenRouter listing Qwen (Alibaba) pricing page
Across fru.devCompany profile

Questions

How much does Qwen3 Max Thinking cost?

$0.78 per million input tokens and $3.9 per million output tokens.

What is the context window of Qwen3 Max Thinking?

262K tokens, with up to 66K tokens of output.

Has Qwen3 Max Thinking's price changed?

Yes. The output price went from $6 to $3.9, first seen Mar 6, 2026.

List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Weekly: LLM API list prices that changed, Thursday mornings.