whichllm — Browse and compare AI model specs and pricing

Venice AI

Mercury 2

mercury

Model ID mercury-2
Provider Venice AI
Family mercury
Status -
Knowledge Cutoff -
Release Date 2026-02-20
Input Modalities text
Output Modalities text
Context Window 128000
Input Limit -
Output Limit 50000
Tool Calling Yes
Reasoning Yes
Structured Output Yes
Temperature Control Yes
Open Weights No
Input Cost / 1M tokens $0.31
Output Cost / 1M tokens $0.94
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens $0.03
Cache Write Cost / 1M tokens -