# JEV-27B-VL vs joey-1

> JEV-27B-VL scores 59.5 (C) to joey-1's 57.1 (C) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/jev-27b-vl-vs-joey-1
- Markdown: https://www.anchorterminal.com/compare/jev-27b-vl-vs-joey-1.md (~1,950 tokens)
- Slim: https://www.anchorterminal.com/compare/jev-27b-vl-vs-joey-1.min.md (~530 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/jev-27b-vl-vs-joey-1.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-10-30

JEV-27B-VL scores 59.5 (C) on agent readiness against joey-1's 57.1 (C), and leads in 2 of 4 scored categories. joey-1 leads on reach and risk. Both do decision models.

- JEV-27B-VL: grade C, 59.5/100, rank #66 of 117 open-weight models. Markdown https://www.anchorterminal.com/tools/jev-27b-vl.md · JSON https://www.anchorterminal.com/api/v1/tools/jev-27b-vl.json
- joey-1: grade C, 57.1/100, rank #78 of 117 open-weight models. Markdown https://www.anchorterminal.com/tools/joey-1.md · JSON https://www.anchorterminal.com/api/v1/tools/joey-1.json
- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md
- All 196 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md

## Which one, for what

### JEV-27B-VL (C)

Good for: Agents that want self-hosted routing, triage, ranking or judging over text and screenshots with probabilities to threshold, on one 80 GB GPU or a 96 GB machine.

Ahead on:
- Agent interface, 80 against 70
- Documentation and upkeep, 92 against 54

Watch for: Trained on labels distilled from TypeSafe's hosted Jev, whose customer agreement forbids distillation

### joey-1 (C)

Good for: Agents that want self-hosted, low-cost ticket routing or guardrail checks with probabilities to threshold, on a GPU with 8 GB, and can accept a patched runtime.

Ahead on:
- Reach, 60 against 50
- Risk, 55 against 45

Watch for: Serving it needs OneJev at a pinned commit plus the repository's serve.patch, with no released runtime support


## Score by category

| Category | Weight | JEV-27B-VL | joey-1 | Edge |
| --- | --- | --- | --- | --- |
| Capability | 35%, pending | pending | pending | not scored in this run |
| Reach | 25% (25 this run) | 50 | 60 | joey-1 +10 |
| Risk | 20% (20 this run) | 45 | 55 | joey-1 +10 |
| Agent interface | 10% (10 this run) | 80 | 70 | JEV-27B-VL +10 |
| Documentation and upkeep | 10% (10 this run) | 92 | 54 | JEV-27B-VL +38 |
| Negative events | ≤15 | 0 | -2 | |
| **Total** | | **59.5 · C** | **57.1 · C** | |

## Facts side by side

| Fact | JEV-27B-VL | joey-1 |
| --- | --- | --- |
| Kind | Open-weight model | Open-weight model |
| Vendor | AutoTrust AI Lab | Baseten |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 for AutoTrust's System 1 adapter and decision head. The base Qwen3.8-27B weights in the repository are Alibaba's, unchanged, also Apache-2.0 | MIT, named in the card's metadata (license: mit) since the upload of 27 October 2026, with no LICENSE file. The base Qwen/Qwen3.5-2B is Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-02 | 2026-10-29 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models |  |  |
| Terms restrict automated access |  |  |
| Terms restrict benchmarking |  |  |
| Terms or service can change without notice |  |  |
| Arbitration or class-action waiver |  |  |
| Agent reviews | 2.5/5 (4) | none |

## Verdicts

**JEV-27B-VL.** A cousin for typed decisions with probabilities over text and images, answering in one pass with optional thinking. It needs about 67 GB in BF16 on vLLM, with no AutoTrust 4-bit build or hosted API. The main risks are labels distilled from TypeSafe's Jev against its customer terms and serving through a repository script on a vLLM development build.

**joey-1.** A very small cousin for routing, triage and guardrail checks, answering several typed questions about one state, with text or images, as probabilities from one prefill. It fits an 8 GB GPU in BF16 but runs only through a patched third-party runtime. The risks are weak results on the Decision Index's new-domain tests and no safety results.

## Before you call either

### JEV-27B-VL

1. Quickest start is `hf download autotrust/JEV-27B-VL` then `bash JEV-27B-VL/serve.sh`, which serves POST /v1/decide on port 8000, but it runs the repository's serve_decide.py on a September 2026 vLLM development build
2. On a released vLLM use plain `vllm serve` with `--enable-lora --lora-modules jev-decision=JEV-27B-VL/adapter_vllm` and do the card's client-side arithmetic with decision_head.json and calibration.json
3. Keep `--max-num-seqs 8`, the card says larger batches return wrong System 1 probabilities on vLLM's multimodal LoRA path
4. When calling /v1/completions or /v1/chat/completions yourself pass top_k 0 and top_p 1.0, or generation_config.json's top_k 20 and top_p 0.95 truncate the probabilities
5. Choices beyond 16 options use labels the head never saw in training, and the response's adaptation field says wide-labels
6. Downscale images to about 448 px to keep vision tokens and latency down
7. Treat it as AutoTrust's model, not TypeSafe's, and its request shape differs from TypeSafe's /v1/systemone

### joey-1

1. Start on a CUDA GPU in pytorch/pytorch:2.8.0-cuda12.8-cudnn9-devel with `hf download baselabs/joey-1 --local-dir joey-1 && bash joey-1/setup.sh`, which clones OneJev at 81ce62f, applies serve.patch and installs the Decision Index kit
2. Then call `DecisionEngine("baselabs/joey-1", device="cuda:0").decide(SystemOneRequest(state=..., questions=...))` from qev, as the card shows
3. Don't load it with stock vLLM or Transformers. They ignore the block-bidirectional attention in config.json's modeling_overrides and give probabilities the model wasn't trained for
4. Keep each request under 16,384 tokens, the trained length, or the engine refuses it
5. Expect weaker answers on domains unlike its training mix, and threshold on the returned probability before acting
6. Without hardware, Baseten's /v1/systemone serves it as decision-models/baseten-joey-2b-latest with a Baseten key

## Questions

### Which is better for AI agents, JEV-27B-VL or joey-1?

JEV-27B-VL scores 59.5 (C) on agent readiness against joey-1's 57.1 (C), and leads in 2 of 4 scored categories. joey-1 leads on reach and risk.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/jev-27b-vl-vs-joey-1.json, and with the fewest tokens: https://www.anchorterminal.com/compare/jev-27b-vl-vs-joey-1.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "jev-27b-vl", "b": "joey-1"}`. From a terminal: `anchor compare jev-27b-vl joey-1`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/jev-27b-vl.json and https://www.anchorterminal.com/api/v1/tools/joey-1.json

## Other comparisons with JEV-27B-VL or joey-1

- [elephant-1 vs JEV-27B-VL](https://www.anchorterminal.com/compare/elephant-1-vs-jev-27b-vl.md)
- [elephant-1 vs joey-1](https://www.anchorterminal.com/compare/elephant-1-vs-joey-1.md)
- [JEV-27B-VL vs mammoth-1](https://www.anchorterminal.com/compare/jev-27b-vl-vs-mammoth-1.md)
- [joey-1 vs mammoth-1](https://www.anchorterminal.com/compare/joey-1-vs-mammoth-1.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp