Mercury 2's arrival on OpenRouter added another access channel for Inception's reasoning modelA model trained to think — generating extended internal reasoning before answering — trading time and tokens for accuracy on hard problems.Full definition →. OpenRouter's announcement says Mercury 2 is live there and describes it as a diffusion-based reasoning model built for fast AI agentAn 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.Full definition → loops, coding workflows, and real-time AI. Its model listing shows that the model accepts a reasoning-effort setting, a tools parameter for external tool calls, and a response-format parameter for structured outputForcing a model's response to match a schema, so downstream code can parse it instead of guessing at prose.Full definition →, though the listing does not itself explain how each behaves. Developers who already use OpenRouter can select Mercury 2 there and send those parameters.
Terms in this piece · Glossary
reasoning model — A model trained to think — generating extended internal reasoning before answering — trading time and tokens for accuracy on hard problems.
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.
structured output — Forcing a model's response to match a schema, so downstream code can parse it instead of guessing at prose.
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
