$ diff lfm2-5-24b-a2b inkling
LFM2.5-24B-A2B vs Inkling
Values come from LFM2.5-24B-A2B and Inkling, 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
- 1M
- weights
- open
- $/M in
- —
- $/M out
- —
What actually differs
- Context window
- Inkling takes 1M against 131K — 7.6× more room in a single request.
- Recency
- LFM2.5-24B-A2B shipped 90 days after Inkling (2026-10-13 vs 2026-07-15).
Full spec
| Attribute | LFM2.5-24B-A2B | Inkling |
|---|---|---|
| Developer | Liquid AI | Thinking Machines |
| Released | 2026-10-13 | 2026-07-15 |
| Context window | 131,072 tokens | 1M |
| Pricing | $0.10/M input · $0.05/M cached input · $1.00/M output | not recorded |
| License | not recorded | Apache 2.0 (open-weight) |
| Availability | Downloadable base and post-trained weights; Liquid Playground and API | Hugging Face (BF16 and NVFP4), Tinker (fine-tuning), SGLang, vLLM, llama.cpp, Unsloth |