$ diff beam-1-0 lfm2-5-24b-a2b
Beam 1.0 vs LFM2.5-24B-A2B
Values come from Beam 1.0 and LFM2.5-24B-A2B, where each is cited to its source. This page states no benchmark result and ranks neither model — it puts two published specifications next to each other. Where a lab has not published a figure, the row says so rather than guessing.
ReflectionBeam 1.0
- context
- 1M
- weights
- open
- $/M in
- —
- $/M out
- —
- context
- 131K
- weights
- —
- $/M in
- $0.1
- $/M out
- $1
What actually differs
- Context window
- Beam 1.0 takes 1M against 131K — 7.6× more room in a single request.
- Recency
- Beam 1.0 shipped 3 days after LFM2.5-24B-A2B (2026-10-16 vs 2026-10-13).
Full spec
| Attribute | Beam 1.0 | LFM2.5-24B-A2B |
|---|---|---|
| Developer | Reflection | Liquid AI |
| Released | 2026-10-16 | 2026-10-13 |
| Context window | 1M tokens | 131,072 tokens |
| Pricing | not recorded | $0.10/M input · $0.05/M cached input · $1.00/M output |
| License | Apache 2.0 | not recorded |
| Availability | Open weights; Reflection API public beta; partner endpoints | Downloadable base and post-trained weights; Liquid Playground and API |