$ diff lfm2-5-24b-a2b k2-horizon
LFM2.5-24B-A2B vs K2 Horizon
Values come from LFM2.5-24B-A2B and K2 Horizon, 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.
Liquid AILFM2.5-24B-A2B
- context
- 131K
- weights
- —
- $/M in
- $0.1
- $/M out
- $1
- context
- 524K
- weights
- open
- $/M in
- —
- $/M out
- —
What actually differs
- Context window
- K2 Horizon takes 524K against 131K — 4× more room in a single request.
- Recency
- LFM2.5-24B-A2B shipped 40 days after K2 Horizon (2026-10-13 vs 2026-09-03).
Full spec
| Attribute | LFM2.5-24B-A2B | K2 Horizon |
|---|---|---|
| Developer | Liquid AI | Ifm |
| Released | 2026-10-13 | 2026-09-03 |
| Context window | 131,072 tokens | 524,288 (flagship 375B-A23B, native from midtraining onward) |
| Pricing | $0.10/M input · $0.05/M cached input · $1.00/M output | not recorded |
| License | not recorded | Apache 2.0 (weights and code) |
| Availability | Downloadable base and post-trained weights; Liquid Playground and API | Hugging Face (weights, code, checkpoints, training data where redistributable) |