ActiveModel portfolio
LiquidAI: LFM3-1.7B
Tap a star to rate
Liquid AI · Released 2026-11-06 · v2026-11-06 · Closed · Context 262K tokens
Cadle Score
—
language · unranked
Benchmark average
—
Not enough benchmark results yet
Pricing
Unlisted
no list price
NOT RANKED YET
We only rank a model once it has enough published benchmark results to compare fairly. Everything below is what we do know: pricing, news and any scores that have been published.
LiquidAI: LFM3-1.7B · SPEC & DETAILS
Engineered by Liquid AI
MAKER / PROVIDER
INPUT PRICING
Per Request / Free
OUTPUT PRICING
—
CONTEXT WINDOW
262K tokens
PARAMETER SCALE
MoE / Confidential
LICENSE / ACCESS
Proprietary API
RELEASE DATE
2026-11-06
MODALITY
language
DOCUMENTATION
On file
COMMUNITY REVIEWS
COMMUNITY REVIEWS
Verified ratings and feedback from engineers testing LiquidAI: LFM3-1.7B in production.
4.7(3)
ADD YOUR RATING
5 - Frontier Benchmark
Reviews are shared directly with the developer community.
Nov 5, 2026
Evaluated on high-concurrency tool loops. Token generation remains highly consistent under sustained context load, with minimal prompt drift on complex JSON schemas.
Nov 2, 2026
Observed median TTFT under 320ms on cached prefixes across North American endpoints. Throughput scales linearly past 32k tokens with solid instruction following.
Oct 29, 2026
Passed complex multi-step reasoning constraints without degenerate repetitions. Step-by-step verification fidelity aligns closely with benchmark ground truth.
MODEL COMPARISON
| Metric | |
|---|---|
| Provider | Liquid AI |
| Release | 2026-11-06 |
| Input / 1M | No data yet |
| Output / 1M | No data yet |
| Context | 262K tokens |
| Cadle Cap | No data yet |
| Cap board | Unranked |
DATA PROVENANCE
Scores may use different scales — check the Benchmarks tab for source links.
- Supabase models
- Cadle public observations