Mercury 2

Mercury 2

Archived
Inception🇺🇸inception/mercury-2
Compare

Mercury 2 is Inception Labs' diffusion-based LLM that generates responses in parallel rather than token-by-token, delivering very high throughput (1000+ tokens/second) with a 128K context window. It offers tunable reasoning and native tool use, matching Claude Haiku/Gemini Flash-class quality at much faster speeds and lower cost, ideal for latency-sensitive agentic and coding tasks.

Released
Mar 4, 2026
Input
Text
Output
Text
Support
ReasoningTool callingStructured outputs

Performance

Median latency and throughput measured across recent requests.

Throughput512 tok/s
Latency6.49s

Latest news about Mercury 2

Recent articles and community posts, linked to their original sources.