AI Agent StoreLiquid AI · Open-weight decision checkpoint
Liquid d1 3B
A local decision checkpoint for text and images. It returns fixed answers in one pass rather than writing a response.
Released 2026-10-07 · First reviewed 2026-10-09 · Checked 2026-10-15.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on records with known answers, including cases that should go to a person.
What you can use today
You download the model files and supply the hardware and software to run them. Capacity is the amount of information a request can contain; settings and available memory can limit what fits.
Exact checkpoint ID: LiquidAI/d1-3B. Use the checkpoint’s supplied decision interface and matching preprocessing. Generic Hugging Face chat examples do not establish a supported generative chat contract.
Weights use the LFM Open License v1.0, with a commercial-use revenue limitation; review the exact checkpoint license before deployment. Provider benchmark and device timings are not independent measurements. Hosted token prices are unknown; local inference has hardware and operating costs.
The model card documents 32,768 context tokens for d1-3B.
Output: Choice, Score and Noul probabilities without generated output tokens. Compare decision models, limits and input costs ↗
No public hosted per-token quote is verified for this exact checkpoint. It is not the hosted d1 API and does not inherit its $0.04 rate.
Provider release and specifications ↗
Check availability and plans ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Include the time and hardware needed to run it.
Compare caching and long-context costs ↗