# Liquid d1 vs SPEV (slim)

> SPEV scores 51.1 (D) to Liquid d1's 43.5 (E) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/liquid-d1-vs-sprag-spev.md (~2,600 tokens) · this version ~630 tokens · JSON https://www.anchorterminal.com/compare/liquid-d1-vs-sprag-spev.json · canonical https://www.anchorterminal.com/compare/liquid-d1-vs-sprag-spev
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-15
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

SPEV scores 51.1 (D) on agent readiness against Liquid d1's 43.5 (E), and leads in 4 of 7 scored categories. Liquid d1 leads on maintenance & community. Both do decision models.

- Liquid d1: E 43.5, rank #968 of 1094 · https://www.anchorterminal.com/tools/liquid-d1.min.md
- SPEV: D 51.1, rank #819 of 1094 · https://www.anchorterminal.com/tools/sprag-spev.min.md
- Liquid d1, 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. Ahead on Maintenance & community, 60 against 49.
- SPEV, good for Typed decisions over raw audio, such as end-of-turn detection, call triage and flagging, plus text and single images, hosted or self-hosted. Ahead on Reliability, 45 against 21; Schema & documentation, 81 against 59; Agent ergonomics, 76 against 63.

| Category | Liquid d1 | SPEV |
| --- | --- | --- |
| Reliability (16%) | 21 | 45 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 59 | 81 |
| Agent ergonomics (13%) | 63 | 76 |
| Security & auth (14%) | 35 | 33 |
| Payments & pricing (10%) | 27 | 30 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 60 | 49 |
| Transparency & trust (7%) | 54 | 54 |

| Fact (where they differ) | Liquid d1 | SPEV |
| --- | --- | --- |
| Vendor | Liquid AI | Sprag |
| Hosted endpoint | `https://api.liquid.ai/decisions/v1/systemone` | `https://api.sprag.ai/v1/decisions` |
| Pricing | Freemium | Pay per use |
| Licence | 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 | Apache-2.0 (weights and inference code, following the Qwen3-Omni base). Training code and data aren't published |
| Last release | 2026-10-07 | 2026-10-14 |
| Terms last updated | 2026-09-30 | 2026-09-01 |
| Privacy policy last updated | 2026-09-30 | 2026-08-01 |
| Customer content may train models | yes | yes, with an opt-out |