Mercury 3

Inception
mercury-3
Released Oct 19, 2026
Providers
1
Context
1.0M
Input
$0.10/M
Output
$0.35/M

Mercury 3 is Inception's most capable diffusion LLM, over 40 times the size of Mercury 1 and generating more than 1,000 tokens per second, with quality on par with frontier speed-optimized models across a 1M-token context.

InceptionDeprecating on Inception

inception/mercury-3QuantUnspecified
Input
$0.10/M
Output
$0.35/M
Context
1.0M
Max out
131K
Cache read
$0.01/M
Cache write
$0.10/M
Thinking out
$0.35/M