Inception
Inception: Mercury 2
Descripción del proveedor (EN)
Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...
ActivoFuente oficial ↗
FICHA TÉCNICA
Datos normalizados
- Id
- inception/mercury-2
- Name
- Inception: Mercury 2
- Provider
- Inception
- Family
- mercury
- Source
- openrouter
- Created Unix
- 1772636275
- Knowledge Cutoff
- —
- Context Length
- 128000
- Source Id
- inception/mercury-2
- Canonical Slug
- inception/mercury-2-20260304
- Provider Slug
- inception
- Variant
- —
- Is Free
- False
- Max Completion Tokens
- 50000
- Modality
- text->text
- Tokenizer
- Other
- Instruct Type
- —
- Is Moderated
- False
- Supported Parameters
- ["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"]
- Default Parameters
- {"temperature":0.75,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}
- Reasoning
- {"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"}
- Expiration Date
- —
- Hugging Face Id
- —
- Links
- {"details":"/api/v1/models/inception/mercury-2-20260304/endpoints"}
- Supports Tools
- True
- Supports Structured Outputs
- True
- Supports Reasoning
- True
- Supports Vision
- False
- Supports Audio
- False
- Supports Video
- False
- Supports Files
- False