All Models

Qwen3 Max

qwen Reasoning Tool Calling Structured Output

Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It delivers higher accuracy in math, coding, logic, and science tasks, follows complex instructions in Chinese and English more reliably, reduces hallucinations, and produces higher-quality responses for open-ended Q&A, writing, and conversation. The model supports over 100 languages with stronger translation and commonsense reasoning, and is optimized for retrieval-augmented generation (RAG) and tool calling, though it does not include a dedicated “thinking” mode.

Providers 11
Released Jan 1, 2025
Input Modalities text
Output Modalities text
Tarsk Use coding

Available Providers (11)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Alibaba Coding Plan qwen3-max-2026-01-23 $0.00/MTok $0.00/MTok 262.1K 32.8K
iFlow qwen3-max $0.00/MTok $0.00/MTok 256K 32K
Alibaba Coding Plan (China) qwen3-max-2026-01-23 $0.00/MTok $0.00/MTok 262.1K 32.8K
AIHubMix qwen3-max-2026-01-23 $0.34/MTok $1.37/MTok 262.1K 65.5K
Alibaba (China) qwen3-max $0.86/MTok $3.44/MTok 262.1K 65.5K
Alibaba qwen3-max $1.20/MTok $6.00/MTok 262.1K 65.5K
Abacus qwen3-max $1.20/MTok $6.00/MTok 131.1K 16.4K
OpenRouter qwen/qwen3-max $1.20/MTok $6.00/MTok 262.1K 32.8K
Vercel AI Gateway alibaba/qwen3-max $1.20/MTok $6.00/MTok 262.1K 32.8K
NovitaAI qwen/qwen3-max $2.11/MTok $8.45/MTok 262.1K 65.5K
Qiniu qwen3-max /MTok /MTok 262.1K 65.5K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output