QwenQwen 3Open SourceArena #34Sep 23, 2025

Qwen3 Max

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.

Context Window
262K
tokens
Max Output
66K
tokens
Released
Sep 23, 2025
Arena Rank
#34
of 305 models

Capabilities

👁Vision
🧠Reasoning
🔧Tool Calling
Prompt Caching
🖥Computer Use
🎨Image Generation

Supported Parameters

Max Tokens
Output length limit
Presence Penalty
Encourage new topics
Response Format
JSON mode / structured output
Seed
Deterministic outputs
Temperature
Controls randomness
Tool Choice
Control tool usage
Tool Calling
Function calling support
Top P
Nucleus sampling

Pricing Comparison

RouterInput / 1MOutput / 1MCached Input / 1M
Requesty$0.86$3.44
OpenRouter$1.20$6.00$0.24
Vercel AI$0.84$3.38
Martian$1.20$6.00$0.24
DeepInfra$1.20$6.00$0.24

Model IDs

Requestyalibaba/qwen3-max
OpenRouterqwen/qwen3-max

Tags

visiontool-callingcaching
Compare with another model

Related Models