Model tracker / Decision models / Liquid AI
d1
d1 is a closed decision model from Liquid AI: it answers typed questions, such as yes or no, pick one or pick several, with probabilities instead of writing text. It costs $0.04 per million input tokens (Liquid AI, OpenRouter, Vercel AI Gateway), and output is free. It scores 74.4 on the independent JevBench Capability Score (board v1.7.46), where Jev, the reference, scores 77.1.
- Made by
- Liquid AI
- Weights
- Closed
- Size
- Undisclosed
- Where
- Liquid AI, OpenRouter, Vercel AI Gateway
- Images
- Yes
- Context
- 65,536
- Fine-tuning
- None ("not trainable")
d1 price
US dollars per million input tokens. Decision models don't write text, so none of the hosted ones charge for output.
| Where | Input | Output | Notes | Checked |
|---|---|---|---|---|
| Liquid AI, OpenRouter, Vercel AI Gateway | $0.04 | Free | Via Vercel's AI Gateway; there's also a free, text-only model (d1:free). | 2026-10-14 |
d1 benchmarks
| Benchmark | Result | What it measures | Reported by |
|---|---|---|---|
| JevBench v1.7.46 | 74.4 | Capability Score: accuracy and calibration on typed decisions, with Jev as the reference system | Independent |
| JevBench time | 0.27 s | Seconds per decision: measured end to end for hosted APIs, the board's estimate for self-hosted models | Independent |
Makers' speeds are measured on their own hardware and aren't comparable with each other or with JevBench's timings.
Decision models like d1
Every other decision model we track, by independent JevBench score.
| Model | Input / M | JevBench | Weights |
|---|---|---|---|
| d1 | $0.04 | 74.4 | Closed |
| Jev 1.13 TypeSafe AI | $0.042 | 77.1 | Closed |
| Clef Cloudflare | $0.24 | 75.3 | Open |
| OpenAI Decisions (GPT-6 Luna) OpenAI | $0.10 | 73.5 | Closed |
| Microsoft-Decision-1 Microsoft | $0.042 | 70.8 | Closed |
| Clef-flash Cloudflare | $0.038 | 63.8 | Open |
| Clef-omni Cloudflare | $0.15 | 58.3 | Open |
| d1-3B Liquid AI | Self-host | 49.5 | Open |
| d1-omni-600M (experimental) Liquid AI | Self-host | 32.8 | Open |
| Laya Convai Innovations | Free | 32.5 | Open |
| CLM-8B Stanford and NVIDIA | Self-host | 20.1 | Open |
| Strands Decider 2B AWS Strands Labs | Self-host | – | Open |
Compare them all in the decision models table →
d1 on dbggr
- Haiku 5.5 and four-cent decision models: the AI price war reaches the bottom tier Saturday edition, 2026-10-10
- Microsoft enters decision models at Jev's price as TypeSafe raises $870M Daily, 2026-10-09
- A database per agent: Turso, Neon, Supabase, Cloudflare D1 and Durable Objects compared on idle cost, limits and cold starts Article, 2026-10-08
- Claude Haiku 5.5 launches at $0.10 per million tokens, matching GPT-6 Luna Daily, 2026-10-07
- OpenAI publishes 722 AI-written math papers, claiming proofs of the quasi-Riemann hypothesis and Unique Games Daily, 2026-10-06
- Stop asking your LLM multiple-choice questions: a guide to decision models Article, 2026-10-02
d1 FAQ
How much does d1 cost?
d1 costs $0.04 per million input tokens at Liquid AI, OpenRouter, Vercel AI Gateway. Via Vercel's AI Gateway; there's also a free, text-only model (d1:free). Checked 14 October 2026.
Is d1 open weight?
No. d1 is only available through Liquid AI, OpenRouter, Vercel AI Gateway.
How fast is d1?
Liquid AI doesn't publish a latency figure. JevBench gives 0.27 seconds per decision, measured end to end.
How does d1 compare with Jev?
On JevBench's Capability Score (board v1.7.46), d1 scores 74.4 against Jev's 77.1. Jev costs $0.042 per million input tokens; d1 costs $0.04. JevBench is a one-person project that uses Jev as its reference, which favours cheap hosted models.