Model tracker / Decision models / Jared Palmer
Kev-9B
Open-weight 9B decision model on Qwen3.5 with Jev's API, for a bigger GPU
Kev-9B is an open-weight decision model from Jared Palmer (Apache 2.0, plus training code and eval suites, 9B, a LoRA adapter on Qwen3.5-9B-Base parameters): it answers typed questions, such as yes or no, pick one or pick several, with probabilities instead of writing text. There's no hosted version: you run it on your own hardware. JevBench, the main independent benchmark, doesn't list it yet.
- Made by
- Jared Palmer
- Weights
- Open, Apache 2.0, plus training code and eval suites
- Size
- 9B, a LoRA adapter on Qwen3.5-9B-Base
- Where
- Self-host only
- Images
- No, text only
- Context
- 65,536 (accuracy validated to 8,192)
- Fine-tuning
- Full recipe and a fine-tuning skill for coding agents published
Kev-9B 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 |
|---|---|---|---|---|
| Self-host only | Self-host | – | – | 2026-10-25 |
Kev-9B speed
| Measure | Result | Reported by |
|---|---|---|
| Reported speed | 24.0 ms model time for six questions on an H100 | Jared Palmer |
Measured by the maker on its own hardware; JevBench doesn't list this model yet.
Decision models like Kev-9B
Every other decision model we track, by independent JevBench score.
| Model | Input / M | JevBench | Weights |
|---|---|---|---|
| Kev-9B | Self-host | – | Open |
| Mammoth-1 Baseten (Base Labs) | Free | 85.2 | Open |
| Perplexity Decider V1.2 Perplexity | $0.02 | 80.8 | Open |
| d1-ultra Liquid AI | $0.042 | 80.5 | Closed |
| Kev-27B Jared Palmer | Self-host | 78.9 | Open |
| Clef Cloudflare | $0.24 | 75.3 | Open |
| Jev 1.14 TypeSafe AI | $0.042 | 75.0 | Closed |
| d1 Liquid AI | $0.02 | 74.4 | Closed |
| Mercury Decide Inception | $0.02 | 73.6 | Closed |
| OpenAI Decisions (GPT-6 Luna) OpenAI | $0.10 | 73.5 | Closed |
| Microsoft-Decision-1 Microsoft | $0.042 | 70.8 | Closed |
| Elephant-1 Baseten (Base Labs) | Free | 70.2 | Open |
| Strands Decider 26B-A4B AWS Strands Labs | Self-host | 66.7 | Open |
| Clef-flash Cloudflare | $0.038 | 63.8 | Open |
| Perplexity Decider Flash V1.2 Perplexity | $0.01 | 61.7 | 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 |
| Clairic Cloudflare | $0.10 | – | Closed |
| Kev-0.8B Jared Palmer | Self-host | – | Open |
| Kev-4B Jared Palmer | Self-host | – | Open |
| Strands Decider 2B AWS Strands Labs | Self-host | – | Open |
Compare them all in the decision models table →
Kev-9B FAQ
How much does Kev-9B cost?
Kev-9B has no hosted, per-token price: you download it and run it yourself, so the cost is your own compute.
Is Kev-9B open weight?
Yes. Jared Palmer publishes the weights under Apache 2.0, plus training code and eval suites, so you can run and fine-tune it yourself.
How fast is Kev-9B?
Jared Palmer reports 24.0 ms model time for six questions on an H100, measured on its own hardware.
How does Kev-9B compare with Jev?
JevBench doesn't list Kev-9B yet, so there's no independent comparison. Jev costs $0.042 per million input tokens; Kev-9B is self-host only.