Minimax
MiniMax: MiniMax M1
Descripción del proveedor (EN)
MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...
ActivoFuente oficial ↗
FICHA TÉCNICA
Datos normalizados
- Id
- minimax/minimax-m1
- Name
- MiniMax: MiniMax M1
- Provider
- Minimax
- Family
- minimax-m1
- Source
- openrouter
- Created Unix
- 1750200414
- Knowledge Cutoff
- 2024-06-30
- Context Length
- 1000000
- Source Id
- minimax/minimax-m1
- Canonical Slug
- minimax/minimax-m1
- Provider Slug
- minimax
- Variant
- —
- Is Free
- False
- Max Completion Tokens
- 40000
- Modality
- text->text
- Tokenizer
- Other
- Instruct Type
- —
- Is Moderated
- False
- Supported Parameters
- ["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"]
- Default Parameters
- {"temperature":null,"top_p":null,"frequency_penalty":null}
- Reasoning
- {"mandatory":false}
- Expiration Date
- —
- Hugging Face Id
- —
- Links
- {"details":"/api/v1/models/minimax/minimax-m1/endpoints"}
- Supports Tools
- True
- Supports Structured Outputs
- False
- Supports Reasoning
- True
- Supports Vision
- False
- Supports Audio
- False
- Supports Video
- False
- Supports Files
- False