Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Mercury 2.5 is available | Read the announcement →
Choose how much Mercury reasoning models deliberate before responding, from near-instant answers to deeper multi-step reasoning.
reasoning_effort controls how much the model deliberates before answering. It applies to mercury-2.5 and mercury-2 on the chat completions endpoint and accepts four values:
| Value | Latency | Best for |
|---|---|---|
instant | Lowest | Voice, realtime turns, high-volume automations |
low | Low | Latency-sensitive chat and tool-calling |
medium (default) | Balanced | General-purpose use |
high | Highest | Complex, multi-step reasoning |
reasoning_effort is omitted, the model uses medium.Was this page helpful?