Mercury Coder Small
mercury-coder-small
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
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| nano-gpt | $0.25 | $1.00 | $0.125 | — | 33K | 16K | — |
| vercel · inception | $0.25 | $1.00 | — | — | 32K | 16K | — |
| vercel_ai_gateway · vercel-ai-gateway | $0.25 | $1.00 | — | — | 32K | 16K | — |