modelbenchmark.io

Mercury Coder Small

mercury-coder-small

Compare

Model by Inception AI. A diffusion large language model that runs incredibly quickly (500+ tokens/second) while matching Claude 3.5 Haiku and GPT-4o-mini. 1st in speed on Copilot arena, and matching 2nd in quality.

Specification

most-agreed values

Context
33K
Max output
16K
Released
2024-01-01
Knowledge cutoff
Retires
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.25
Output
$1.00
Cache read
$0.125

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt$0.25$1.00$0.12533K16K
vercel · inception$0.25$1.0032K16K
vercel_ai_gateway · vercel-ai-gateway$0.25$1.0032K16K