Mercury 2.5
Mercury 2.5 is Inception Labs' diffusion based large language model that generates text in parallel rather than sequentially, reaching over 1,100 tokens per second. It features tunable reasoning, a 260K token context window, native tool use with parallel function calling, and schema aligned JSON output, built for latency sensitive applications such as search agents, RAG pipelines, and voice agents.
- Type
- Text
- Weights
- Open
More from Inception Labs
5
About Inception Labs
1
Inception’s breakthrough diffusion-based approach to language generation enables the world’s fastest, most efficient AI models with best-in-class quality.