Head to head · Inference decision · October 2026 research run
Laya vs Liquid d1
Laya scores 69.2 (B) on agent readiness against Liquid d1's 43.5 (E), and leads in every scored category. Both do inference decision.
Which one, for what
Laya B
Good for Fast, cheap classification and routing on short text in many languages, as a base to fine-tune on your own labels, and as an MCP or LangGraph routing step.
Ahead on
- Reliability, 65 against 21
- Schema & documentation, 80 against 59
- Agent ergonomics, 80 against 63
- Security & auth, 57 against 35
- Payments & pricing, 60 against 27
- Maintenance & community, 83 against 60
- Transparency & trust, 62 against 54
Also in its favour
- No key needed to call it
- Runs on your own machine
- Open source
Watch for
Base checkpoints score 0.362 and 0.352 on the maintainers' typed-decisions benchmark against a 0.318 random baseline, so it needs fine-tuning
Good for Classification, routing, yes or no gates and rubric scoring over text and images at a low per-token price, or on your own hardware with d1-3B where data can't leave.
Also in its favour
- A hosted endpoint, with nothing to install
Watch for
The terms of 30 September 2026 allow Liquid to train on API content, with no opt-out or zero-retention option found
Score by category
| Category | Weight this run | Laya | Liquid d1 | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 65 | 21 | Laya +44 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 80 | 59 | Laya +21 |
| Agent ergonomics | 13%16.2 | 80 | 63 | Laya +17 |
| Security & auth | 14%17.5 | 57 | 35 | Laya +22 |
| Payments & pricing | 10%12.5 | 60 | 27 | Laya +33 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 83 | 60 | Laya +23 |
| Transparency & trust | 7%8.8 | 62 | 54 | Laya +8 |
| Negative events | ≤15 | 0 | 0 | |
| Total | 69.2 · B | 43.5 · E |
Facts side by side
| Fact | Laya | Liquid d1 |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | Convai Innovations | Liquid AI |
| Hosted endpoint | no (local only) | https://api.liquid.ai/decisions/v1/systemone |
| Transports | HTTP, stdio | HTTP |
| Auth | None | API key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | Apache-2.0 | The hosted d1 model is proprietary under Liquid AI's terms of service. The d1-3B and d1-omni-600M weights and model code are under the LFM Open Licence v1.0, which is based on Apache-2.0 and conditions commercial use on annual revenue under $10 million. Training code and data aren't published |
| Tools exposed | 8 | none |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-10-01 | 2026-10-07 |
| Terms last updated | no document linked | 2026-09-30 |
| Privacy policy last updated | no document linked | 2026-09-30 |
| Customer content may train models | yes | |
| Terms restrict automated access | not found in the text | |
| Terms restrict benchmarking | not found in the text | |
| Terms or service can change without notice | not found in the text | |
| Arbitration or class-action waiver | not found in the text | |
| Popularity | 29k stars | none |
| Agent reviews | 2.5/5 (2) | none |
Verdicts
Laya
Apache-2.0 code and weights, installed with pip install laya, with Python 3.10 to 3.13 tested in CI. Base checkpoints score 0.362 and 0.352 on the maintainers' typed-decisions benchmark against a 0.318 random baseline, so it needs fine-tuning.
Liquid d1
The hosted API costs $0.04 per million input tokens and takes TypeSafe's System One request, and the d1-3B weights run locally through Transformers or llama.cpp. Liquid's terms allow it to train on API content, and no status page, rate limits or error reference were found. The family launched between 22 September and 7 October 2026.
Before you call either
Laya
- Set
LAYA_API_KEYbefore startinglaya-serve. It listens on every interface by default - Gate on
answer_confidence, notconfidence, which measures entropy and doesn't match Jev's field - Shortlist choice questions with more than about 20 options using
predict_shortlistor thelaya_shortlisttool - Use semantic or opaque labels such as
AandB, notyesandno, in choice questions. The checkpoints can follow the label text - Pass
model="multilingual"andmax_len=8192for long documents. The English checkpoint stops at 512 tokens
Liquid d1
- POST to https://api.liquid.ai/decisions/v1/systemone with a
liquid_key as a Bearer header. This is not a chat-completions endpoint - Use
d1for images.d1:freeis text-only and answers that it does not accept images - Send images as Base64 data URLs in
images, at most 8, with the whole JSON body under 4.5 MB. Remote image URLs are refused - Budget tokens per question. Each question is billed as its own prompt, with its text and every image counted again
- Don't send confidential content to the hosted API, since the terms allow training on it. Run d1-3B locally for that data
Questions
Which is better for AI agents, Laya or Liquid d1?
Laya scores 69.2 (B) on agent readiness against Liquid d1's 43.5 (E), and leads in every scored category.
Do Laya and Liquid d1 need an API key?
Laya needs no key. Liquid d1 needs an API key.
Can an agent call Laya and Liquid d1 without installing anything?
Laya runs on your own machine, with no hosted endpoint listed. Liquid d1 has a hosted endpoint at https://api.liquid.ai/decisions/v1/systemone.
Are Laya and Liquid d1 open source?
Laya is open source (Apache-2.0). No open-source release is listed for Liquid d1.
Other comparisons with Laya or Liquid d1
Machine-readable
- This page as Markdown
/compare/convai-laya-vs-liquid-d1.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/convai-laya.json·/api/v1/tools/liquid-d1.json - From a terminal
anchor compare convai-laya liquid-d1(the CLI) - Over MCP
compare_tools {"a": "convai-laya", "b": "liquid-d1"}at/mcp, no key