Inception Labs releases Mercury 2 for Search with decoding above 1,000 tokens/s
Original title:Mercury 2 for Search: Fast enough to run a hundred times per query
AI summary
Inception Labs released Mercury 2 for search pipelines, featuring diffusion-based parallel decoding above 1,000 tokens/s; it is nearly 2x faster than Gemini 3.1 Flash Lite and 10x faster than GPT-5 Mini across WideSearch steps, priced at $0.25/M input and $0.75/M output.
Key Takeaways
- Inception Labs released Mercury 2 for search pipelines,featuring diffusion-based parallel decoding…
- it is nearly 2x faster than Gemini 3.
- 1 Flash Lite and 10x faster than GPT-5 Mini across WideSearch steps,priced at $0.
- 25/M input and $0.
- 75/M output.
Quick Facts
- Published
- Updated
- Source
- Inception Labs:Blog(网页)
- Category
- Model Releases
- AI score
- 63
原文给出每步延迟、成本与检索消融数据,读者可据此评估扩散模型在搜索管线中的实际取舍。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Inception Labs releases Mercury 2 for Search with decoding above 1,000 tokens/s. August 11, 2026. https://new.nat6.net/en/news/ud6g8nqdmfnr1t51sujqdm5v9/