What the vendor claims, next to what independent boards measured. The two are never mixed in one column.
Source: OpenRouter, as of Oct 28, 09:19 UTC. Model page on OpenRouter
Quoted word for word from the vendor's own launch post or model card. Claims, not measurements.
No vendor claims recorded yet. They come from launch posts and model cards the Drops covered.
Measured by independent sources (Epoch AI, LMArena, OpenRouter's benchmark runs, τ²-bench, Vectara), not by the vendor. "Listed as" is the source's own name for the model, so you can check our match.
No independent results yet. They appear here as Epoch AI and LMArena add this model.
OpenRouter's list price per 1M tokens in each of our snapshots.
Unchanged across our 29 snapshots.
| Snapshot | Input $/1M | Output $/1M |
|---|---|---|
| Oct 28, 09:22 UTC | $0.05 | $0.7 |
| Oct 27, 16:03 UTC | $0.05 | $0.7 |
| Oct 27, 04:03 UTC | $0.05 | $0.7 |
| Oct 26, 16:04 UTC | $0.05 | $0.7 |
| Oct 26, 04:03 UTC | $0.05 | $0.7 |
| Oct 25, 16:04 UTC | $0.05 | $0.7 |
| Oct 25, 06:03 UTC | $0.05 | $0.7 |
| Oct 24, 15:04 UTC | $0.05 | $0.7 |
| Oct 24, 03:03 UTC | $0.05 | $0.7 |
| Oct 23, 15:03 UTC | $0.05 | $0.7 |
| Oct 23, 03:04 UTC | $0.05 | $0.7 |
| Oct 22, 15:03 UTC | $0.05 | $0.7 |
| Oct 22, 05:04 UTC | $0.05 | $0.7 |
| Oct 21, 15:03 UTC | $0.05 | $0.7 |
| Oct 21, 03:02 UTC | $0.05 | $0.7 |
| Oct 20, 15:04 UTC | $0.05 | $0.7 |
| Oct 20, 03:03 UTC | $0.05 | $0.7 |
| Oct 19, 15:04 UTC | $0.05 | $0.7 |
| Oct 19, 10:50 UTC | $0.05 | $0.7 |
| Oct 18, 15:03 UTC | $0.05 | $0.7 |
| Oct 18, 03:05 UTC | $0.05 | $0.7 |
| Oct 17, 15:03 UTC | $0.05 | $0.7 |
| Oct 17, 03:03 UTC | $0.05 | $0.7 |
| Oct 16, 15:02 UTC | $0.05 | $0.7 |
| Oct 16, 03:03 UTC | $0.05 | $0.7 |
| Oct 15, 17:02 UTC | $0.05 | $0.7 |
| Oct 15, 03:02 UTC | $0.05 | $0.7 |
| Oct 14, 15:03 UTC | $0.05 | $0.7 |
| Oct 14, 03:02 UTC | $0.05 | $0.7 |
Source: OpenRouter, as of Oct 28, 09:22 UTC
OpenRouter lists liquid/lfm-2.5-24b-a2b at $0.05 in / $0.7 out per 1M tokens with 128000 context. Liquid AI posted on X that it has 24B total parameters with 2B active per token.
Why it matters: A low-cost option for agents on laptops and PCs. Hugging Face also ran Liquid AI's post: Run fast, private agents on-device with LFM2.5-24B-A2B.
From Drop #023 · Wed, Oct 14 · Morning