Mercury 2
By inception
inception/mercury-2A diffusion-based reasoning LLM that generates text via parallel refinement (not token-by-token), delivering real-time latency with ~1k tokens/sec plus 128K context and built-in tool/JSON support.
ReleasedFeb 24, 2026
Pricing
Pricing (Input)$0.25/M
Pricing (Output)$0.75/M
CachingYes
Limits
Context Length128K
Max Output Tokens128K
Input Modalities
TextSupported
ImageNot supported
PDFNot supported
AudioNot supported
Output Modalities
TextSupported
ImageNot supported
AudioNot supported
Features
ReasoningSupported
ToolsSupported
TemperatureSupported