Mercury 2
mercury-2
Compact GPT model for low-latency assistance and high-volume workloads
Specification
most-agreed values
Context
128K
Max output
50K
Released
2024-01-01
Knowledge cutoff
2025-01-01
Retires
—
Open weights
no
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.25
Output
$0.75
Cache read
$0.025
Available from 7 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| inception | $0.25 | $0.75 | $0.025 | — | 128K | 50K | — |
| inception · inception | $0.25 | $0.75 | $0.025 | — | 128K | 50K | — |
| kilo · inception | $0.25 | $0.75 | $0.025 | — | 128K | 50K | — |
| nano-gpt | $0.25 | $0.75 | $0.025 | — | 128K | 50K | — |
| openrouter · inception | $0.25 | $0.75 | $0.025 | — | 128K | 50K | — |
| vercel · inception | $0.25 | $0.75 | $0.025 | — | 128K | 128K | — |
| venice | $0.3125 | $0.9375 | $0.0312 | — | 128K | 50K | — |
