Inception's August 2025 platform update gave API users a spending control that could stop further requests. Users could set a billing limit, receive an email when spending reached 80% of it, and have requests blocked at the limit. That makes the setting an operating constraint for an application: reaching the cap affects whether it can continue calling the model. Teams using the feature therefore need to choose a limit that reflects both their budget and the service interruption they are prepared to accept. Billing-limit announcement
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.
structured output — Forcing a model's response to match a schema, so downstream code can parse it instead of guessing at prose.
Read the full thread on X 
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
