Beam
reflection-beam
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Specification
most-agreed values
Context
1M
Max output
1M
Released
2026-10-21
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.40
Output
$1.20
Cache read
$0.04
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| digitalocean | $0.40 | $1.20 | $0.04 | — | 1M | 1M | — |