Inception ships Mercury Decide update with ZDR and 66k context

Mercury Decide now has 66k context, GA with zero data retention, and pricing below Jev. Teams with privacy requirements can now use it in production for classification and verification routing.

• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
• 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 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
• postMercury 2 ships as the first reasoning diffusion LLM

• postMercury Decide gets a zero-data-retention endpoint on OpenRouterOpenRouter
• postMercury adds tool calling, 128K context, structured output and spend limitsInception
• postVals AI evaluates Mercury Decide: frontier accuracy at lowest costVals AI

Checking sign-in…

Loading comments…