Qwen
Qwen: Qwen3 30B A3B Thinking 2507
Descripción del proveedor (EN)
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...
ActivoFuente oficial ↗
FICHA TÉCNICA
Datos normalizados
- Id
- qwen/qwen3-30b-a3b-thinking-2507
- Name
- Qwen: Qwen3 30B A3B Thinking 2507
- Provider
- Qwen
- Family
- qwen3
- Source
- openrouter
- Created Unix
- 1756399192
- Knowledge Cutoff
- 2025-06-30
- Context Length
- 81920
- Source Id
- qwen/qwen3-30b-a3b-thinking-2507
- Canonical Slug
- qwen/qwen3-30b-a3b-thinking-2507
- Provider Slug
- qwen
- Variant
- —
- Is Free
- False
- Max Completion Tokens
- 32768
- Modality
- text->text
- Tokenizer
- Qwen3
- Instruct Type
- —
- Is Moderated
- False
- Supported Parameters
- ["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p","structured_outputs"]
- Default Parameters
- {}
- Reasoning
- {"mandatory":true}
- Expiration Date
- 2026-10-09
- Hugging Face Id
- Qwen/Qwen3-30B-A3B-Thinking-2507
- Links
- {"details":"/api/v1/models/qwen/qwen3-30b-a3b-thinking-2507/endpoints"}
- Supports Tools
- True
- Supports Structured Outputs
- True
- Supports Reasoning
- True
- Supports Vision
- False
- Supports Audio
- False
- Supports Video
- False
- Supports Files
- False