← Volver al catálogo
Qwen

Qwen: Qwen3 Max Thinking

Descripción del proveedor (EN)

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...

qwen3-max-thinkingopenrouterPor validar
Contexto262.144 tokens
Publicado09/02/2026
Corte de conocimientoPor validar
EstadoActivo
FICHA TÉCNICA

Datos normalizados

Id
qwen/qwen3-max-thinking
Name
Qwen: Qwen3 Max Thinking
Provider
Qwen
Family
qwen3-max-thinking
Source
openrouter
Created Unix
1770671901
Knowledge Cutoff
—
Context Length
262144
Source Id
qwen/qwen3-max-thinking
Canonical Slug
qwen/qwen3-max-thinking-20260123
Provider Slug
qwen
Variant
—
Is Free
False
Max Completion Tokens
65536
Modality
text->text
Tokenizer
Qwen
Instruct Type
—
Is Moderated
False
Supported Parameters
["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"]
Default Parameters
{"temperature":null,"top_p":null,"frequency_penalty":null}
Reasoning
{"mandatory":false}
Expiration Date
2026-10-09
Hugging Face Id
—
Links
{"details":"/api/v1/models/qwen/qwen3-max-thinking-20260123/endpoints"}
Supports Tools
True
Supports Structured Outputs
True
Supports Reasoning
True
Supports Vision
False
Supports Audio
False
Supports Video
False
Supports Files
False