SargalaySargalay

Command Palette

Search for a command to run...

Back to all models
qwen

Qwen: 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. By significantly scaling model capacity and reinforcement learning compute, it delivers major gains in factual accuracy, complex reasoning, instruction following, alignment with human preferences, and agentic behavior.

qwen/qwen3-max-thinking

Context Size

262.144K

Input Price

4,797 Ks/M

Output Price

23,985 Ks/M


Architecture

Text

Supported Parameters

include_reasoningmax_tokenspresence_penaltyreasoningresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_p

Details

TokenizerQwen
Max Completion32,768 tokens
Provider Context262.144K tokens
ModeratedNo