Inception's API launch made Mercury Coder Small available for two distinct coding interactions: conversation and filling a gap between existing pieces of code. In the second mode, the application supplies the text before and after the gap, and the model generates the missing portion. That gives an editor a way to request a completion that fits surrounding code. The launch article also describes compatibility with OpenAI client libraries, allowing applications to connect through a familiar interface while using Inception's coding model.
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
postInception ships Mercury Decide update with ZDR and 66k context
postInception launches Mercury Voice, a diffusion LLM for low-latency voice agents
postToday, we’re introducing Mercury 2.5, the most capable diffusion LLM on the…
postInception ships Mercury 2.5 Preview at roughly 1,100 tokens per second
