Jev pricing and cost per decision model request
Jev costs $0.042 per million input tokens, with free output.
Pricing questions
How much does Jev cost?
Jev: Published price (vendor-reported): $0.042 per million input tokens; output free
Which decision models offer free API access or a free trial?
Mercury Decide: Vendor-reported facts: Price: $0.02 per million input tokens at a 50% discount, output free; a free tier remains (OpenRouter, as of 22 Oct 2026) Parallel Decisions API: Vendor-reported facts: Access: Hosted API, with a playground; 5,000 free requests to start; Decisions Fast also on OpenRouter from 6 Nov 2026, with a seven-day free promotion LingDT-Decision-1.0: Vendor-reported facts: Price: Ant lists ¥0 per million input and output tokens, with an original input rate of ¥0.20 per million tokens. Checked 04 Nov 2026. The rate is for the 4B test endpoint during a free trial; no trial end date was established. MiniCPM-OCR Jev: Vendor-reported facts: Access: Open weights in BF16, AWQ, GPTQ and GGUF; a free API on ModelBest's platform
Mercury Decide facts · Parallel Decisions API facts · LingDT-Decision-1.0 facts · MiniCPM-OCR Jev facts · Source: openrouter.ai ↗ · Source: parallel.ai ↗ · Source: maas.antdigital.com ↗ · Source: huggingface.co ↗
Is Jev output billed?
Jev: Published price (vendor-reported): $0.042 per million input tokens; output free
How much does Decider 1 cost?
Decider 1: Published price (vendor-reported): $0.03 per million input tokens; output $0
How much does Celeris-1-decision cost?
Celeris-1-decision: Published price (vendor-reported): $0.04 per million input tokens; output free
Cost per decision: work from billed tokens
For an input-token API, multiply the billed input tokens by the price per million, then divide by 1,000,000. Free output removes one charge; it does not make the input free. Count the question and options as well as the state.
Source: openrouter.ai · Source: developers.openai.com
A hypothetical 1,000-decision text workload
Assume 1,000 decisions, each billed for exactly 1,000 input tokens, with no search, cache discount, retries or extra calls. That is 1,000,000 billed input tokens. These are arithmetic examples at vendor-reported rates, not usage receipts or a comparison of answer quality.
- Jev: $0.042 for the workload, or $0.000042 per decision.
- Kev 4B on OpenRouter: $0.042 for the workload, or $0.000042 per decision.
- d1 or d1.1 on OpenRouter: $0.02 for the workload, or $0.00002 per decision.
- OpenAI Decisions API: $0.10 for the workload, or $0.0001 per decision, using the recorded uncached rate.
Jev facts · Kev facts · d1 facts · OpenAI Decisions API facts
Per-call prices buy a different service
Parallel Decisions API is recorded at $1 per 1,000 calls and searches the live web. If each decision takes one call, 1,000 calls cost $1. Its call-wide citations and search access differ from scoring supplied context. A token price and a call price alone cannot tell you which service answers your task well.
Parallel search, citations and limits · Evaluate the same task
Check how questions are billed
Liquid's docs say each question is billed as its own prompt, including the question text and all images. A shared state in your request does not by itself establish shared-state billing. Read the provider's usage fields before applying the hypothetical 1,000-token allowance to your app.
Self-hosting needs a cost record too
Downloadable weights move inference onto hardware you operate. The registry records hardware reports and licence terms, but has no common measurement of utilisation, electricity or operator time. It cannot give a universal buy-versus-host break-even. Record those costs alongside billed tokens and failed or escalated decisions.
A camera example: idle hours change the price
As a hypothetical hosting-cost calculation using the camera report's prices, an always-on g6.xlarge at $0.805 an hour costs about $0.000224 per second ($0.805 divided by 3,600). If it could sustain roughly 2.8 frames per second, its hosting cost per frame would match Gemma 4 on Bedrock at the reported $0.000080 per frame. The AWS article did not measure L4 throughput. Capacity at that rate and actual spending remain unverified.
Strands model and image path · Camera evidence and limits · Task-specific evaluation
Evidence: AWS Builder Center · security-camera comparison · discovered 10 Nov 2026 · Source ↗
A filter saves only the calls it removes
The report replays stored Gemma answers with a Strands filter. Its 0.1 cutoff saves 7% of estimated LLM cost with no accuracy loss on that set. At the reported prices, a hypothetical hosting-cost break-even would require sustained throughput of about 40 frames per second, which the article did not measure. The GPU still handles every frame. Sample mix, image size, spare hardware and required accuracy change that estimate; it excludes operator time and does not establish an OpenAI Decisions API result.
Prices are the rates recorded on each model's page on decisionmodels.ai. Page built 12 Nov 2026.
Compare decision models · What is a decision model? · Jev alternatives
Open-weight models are free to download; you pay for your own hardware. Hosted prices are shown where listed.
Published prices
| Model | Maker | Group | Price | Access / Licence |
|---|---|---|---|---|
| Jev | TypeSafe AI | hosted | $0.042 per million input tokens; output free | Access: Launched in early access; also via OpenRouter |
| Decisions API | OpenAI | hosted | $0.10 per million uncached input tokens; output free | Access: Generally available since 22 Oct 2026; public beta launched 6 Oct; native GPT-Live integration since 15 Oct |
| d1 | Liquid AI | hosted | OpenRouter lists d1 and d1.1 at $0.02 and d1-ultra at $0.042 per million input tokens, output free (as of 28 Oct 2026) | Open weights: d1-3B and d1-omni-600M (7 Oct), then d1-2B and d1-Omni-2B (announced 27 Oct), under the LFM Open License v1.0 |
| Mercury Decide | Inception | hosted | $0.02 per million input tokens at a 50% discount, output free; a free tier remains (OpenRouter, as of 22 Oct 2026) | Access: OpenRouter |
| Solar Decide | Upstage | hosted | OpenRouter lists $0.05 per million input tokens, output $0 (as of 2 Oct 2026); the launch post described a limited-time 50% discount | Access: OpenRouter |
| Span-01 | Respan | hosted | $0.02 per million input tokens; output free | |
| Decider 1 | meraGPT | hosted | $0.03 per million input tokens; output $0 | |
| Microsoft-Decision-1 | Microsoft | hosted | $0.042 per million input tokens; output free | Access: Microsoft Foundry, OpenRouter |
| Clef-omni | Cloudflare | hosted | $0.150 per million input tokens | Access: Cloudflare Workers AI; Clef-flash weights are on Hugging Face |
| Celeris-1-decision | Celeris | hosted | $0.04 per million input tokens; output free | |
| SubQ Snap | Subquadratic | hosted | $0.04 per million input tokens; output free | Access: Subquadratic's API; the Snap 1.1 Baseten listing is a separate route |
| Clairic | Cloudflare | hosted | $0.10 per million input tokens on OpenRouter; output free | Access: Workers AI as @cf/cloudflare/clairic; back on OpenRouter as cloudflare/clairic when checked 4 Nov 2026 |
| Parallel Decisions API | Parallel | hosted | $1 per 1,000 calls (as of 25 Oct 2026) | Access: Hosted API, with a playground; 5,000 free requests to start; Decisions Fast also on OpenRouter from 6 Nov 2026, with a seven-day free promotion |
| Kev | Jared Palmer | open | $0.042 per million input tokens and $0 per million output tokens for jaredpalmer/kev-4b on OpenRouter (VENDOR-REPORTED, 2 Nov 2026) | Licence: Apache-2.0 |
| Decider | Perplexity | open | $0.02 (V1.2) and $0.01 (Flash) per million input tokens on OpenRouter, output free (as of 22 Oct 2026) | Licence: Apache-2.0 |
| Drex 2.0 | Nace.AI | open | $0.03 per million input tokens for Drex 2.0, Drex Max, Max v1.1 and Max Finance, hosted at Nace | Licence: Drex Max weights: Nace.AI Open RAIL-M · Access: Drex Max supports text and images through Python on NVIDIA GPUs. CPU and Apple Silicon runtimes support text only. Max Finance API id: drex-max-finance. |
| Mammoth 1 | Baseten (Base Labs) | open | OpenRouter lists mammoth-1 at $0.10, elephant-1 at $0.035 and joey-1 at $0.01 per million input tokens, output free (as of 30 Oct 2026) | Licence: MIT |
| Hume Audio Decisions API | Hume AI | hosted | $0.47 per million input tokens (audio, questions and context); answers not billed. Hume's billing docs, checked 03 Nov 2026 | Access: Playground; request API access through Hume's waitlist |
| Zoom Decisions API | Zoom | hosted | $0.042 per million tokens for Decisions API; $0.10 for Pro, per Zoom's product page checked 03 Nov 2026 | Access: Zoom AI Services portal and playground; sign-up or login required |
| LingDT-Decision-1.0 | Ant Digital Technologies (蚂蚁数科) | hosted | Ant lists ¥0 per million input and output tokens, with an original input rate of ¥0.20 per million tokens. Checked 04 Nov 2026. The rate is for the 4B test endpoint during a free trial; no trial end date was established. | |
| hs-decide-1-flash | Vectorize (Hindsight) | open | $0.02 per million input tokens on Hindsight Inference; input only | Licence: Apache-2.0 · Access: Open weights; vLLM plugin or Transformers on CPU, Apple Silicon and supported GPUs; hosted POST /v1/systemone |
| Reflex | Morph | hosted | $0.042 per million uncached input tokens; $0.008 cached; output free | Access: POST /v1/systemone on Morph; morph/reflex on OpenRouter |
| Grayson | Finic | hosted | $0.035 per million input tokens for ask and score; creating and calibrating scoring models is free | Access: Hosted POST /v1/ask with model grayson-1; no public weights confirmed |
| Zuse | Bineric | hosted | $0.12 per million input tokens for 9B; $0.75 for 27B; no output tokens | Access: Bineric API; dedicated and on-premises deployments by arrangement |
| Sarvam Prism | Sarvam AI | open | Sarvam API: ₹4 per million input tokens; output free | Licence: Apache-2.0 · Access: Public weights and prism.py; hosted POST /v2/systemone |
| Gemini Decision 1 | Google DeepMind | hosted | Google reports $0.10 per million input tokens; output free. Shared input billed once, plus each question's instructions and criteria | Access: Gemini API in Google AI Studio, including a no-cost prototyping tier; listed on OpenRouter |
Prices not recorded here
Hosted
- Snowflake Decision by Snowflake (hosted): no published price. Access: Private preview in Cortex AI Functions
- Classify-1 by ScaleDown (hosted): no published price. Access: OpenRouter, ScaleDown API
Open weights
- DecisionTune 1.0 by DecisionTune (open): no published price. Licence: Apache-2.0
- Tev1-4B by Together AI (open): no published price. Licence: Code MIT; weights licence being finalised as of 2 Oct 2026
- GLiNER2.5-Decide by Fastino (open): no published price. Licence: Apache 2.0
- Laya by Convai Innovations (open): no published price. Licence: Apache 2.0
- Nimble by Bespoke Labs (open): no published price. Licence: Apache 2.0
- Decision 1.0 by vLLM Semantic Router (open): no published price. Licence: Apache-2.0 (checked on Nox-4B)
- H2O-Lightning-4B by H2O.ai (open): no published price. Licence: Apache-2.0
- Jebadiah v2.1 by frontier-infra (open): no published price. Licence: Apache-2.0
- Lumma-Fev-27B by FrontiersMind (open): no published price. Licence: Apache-2.0
- Granite Switch 4.1 by IBM (open): no published price. Licence: Apache-2.0
- TYGER by NineNineSix (open): no published price. Licence: OpenMDW-1.1
- Talos by Tractian (open): no published price. Licence: Apache-2.0
- Qev 0.8B by labqoat (open): no published price. Licence: Apache-2.0
- Decido 1 family by decido-ai (open): no published price. Licence: Apache-2.0 for the five Gemma/Qwen packages; MIT for the XL adapter, with separate base-model terms
- Arc-decide by Arc53 (DocsGPT) (open): no published price. Licence: MIT, built on Qwen3 (Apache-2.0)
- Valen by Valen Team (open): no published price. Licence: Apache-2.0; licence file included
- Fovea-4B by Sivasuthan (open): no published price. Licence: Apache-2.0
- homi by egma-ai (open): no published price. Licence: Apache-2.0
- Nimbus by Crele (open): no published price. Licence: Apache-2.0, code and weights
- GLiDE by Fastino (open): no published price. Licence: Fastino community licence (not a standard open-source licence) · Access: Weights on Hugging Face, or Fastino's hosted System One API
- UltraBERT Curation by Daniel van Strien (open): no published price. Licence: Apache-2.0
- KnowLine by PelaAI (open): no published price. Licence: Apache-2.0
- Ru-Jev by besktech (beskvladimir-create) (open): no published price. Licence: Code MIT; weights tagged MIT on Hugging Face
- Intern-Decision by InternLM (open): no published price. Licence: Apache-2.0
- MiniCPM-OCR Jev by OpenBMB (open): no published price. Licence: Apache-2.0 · Access: Open weights in BF16, AWQ, GPTQ and GGUF; a free API on ModelBest's platform
- Smaug-Decisions by Abacus.AI (open): no published price. Licence: Apache-2.0
- REAX 1.3 by REAX (open): Hosted price not recorded in this registry. Licence: Apache-2.0 for the blended work, subject to preserved upstream licences and notices; REAX Engine is MIT · Access: Open Hugging Face weights and REAX Engine reax13 mode
- K-Decision-9B by ONYULTEA (open): no published price. Licence: Apache-2.0, declared for the model weights · Access: Public model.safetensors weights and serving code
- Saif 0.8B Lightning by GyrTechnology (open): no published price. Licence: CC BY-NC 4.0; non-commercial · Access: Public decoder and decision-row weights, Python runtime and Decision Index engine
- Horopter beta-3 by Fight Fire with Fire Robotics (open): no published price. Licence: Weights, data recipe and docs: CC BY-NC-SA 4.0; code: MIT · Access: Public weights; Python runtime; /v1/systemone, /v1/clairic and combined /v1/horopter endpoints
- TS-PRGuard by typestrict (Lucas Duarte) (open): no published price. Licence: Apache-2.0 tag on the model card · Access: 164,505,784-byte ONNX file, tokenizer and decision_ai.json; ONNX Runtime or decision_ai for Flutter
- wps-decision-1 by Kingsoft Office (open): no published price. Licence: Apache-2.0; LICENSE and NOTICE shipped · Access: Full BF16 weights and FP32 readout; Transformers or /v1/systemone on the pinned vLLM nightly
- d3-mini-agentcode by stonefish-labs (open): no published price. Licence: Apache-2.0; LICENSE and NOTICE shipped · Access: Merged weights, readout, adapter, extractor, frozen questions and thresholds
- Lory by eltokh7 (open): no published price. Licence: Apache-2.0 tags on both model cards · Access: kev.serve at the pinned Kev revision; /v1/systemone; EDSL survey adapter included
- Glimmer System One by Aryan Srivastava (open): no published price. Licence: Heads and code Apache-2.0; MVTec AD data CC BY-NC-SA 4.0, research use only · Access: Public heads and calibration files; Muse Glimmer 30B required separately; code and demo on GitHub
- laya-slotjudge-m46 by Christophe Cruz, Hussam Ghanem and Hocine Cherifi (open): no published price. Licence: CC BY-SA 4.0 weights · Access: Laya runtime; public model.safetensors, configuration and calibration files
- Cicero by Butler Compute (open): no published price. Licence: Apache-2.0
- Adjudex by NewsBang (open): no published price. Licence: Apache-2.0; serving code credited in NOTICE
- kai-decision / K-IM-Deiction by Songkai (open): no published price. Licence: Apache-2.0
- Kev LUX Places by Yale Cultural Heritage AI (open): no published price. Licence: Apache-2.0 tags on both cards
- d1-qwen-0.6b by Grizzlykw (open): no published price. Licence: Apache-2.0
- Jev-style spam LoRA by Abubakar Abid (open): no published price. Licence: Apache-2.0
- Heimdall D1 V6 by Toby-NoSkillSon (open): no published price. Licence: LFM Open License v1.0; commercial revenue limit applies
- RSI-Jev v7.0-VL family by Shanghua Gao (open): no published price. Licence: Apache-2.0 · Access: Public weights with the RSI-Jev runtime; no causal prefix cache
- Vica Laya by tory-labs (open): no published price. Licence: Apache-2.0 · Access: Self-contained macOS arm64, Linux x86_64 and Windows x86_64 runtime bundles; original float checkpoint for laya 0.4.22. The Laya GGUF is not an Ollama or llama.cpp chat-model package
- Spot Snake decision fine-tunes by Lucasgitguy-co (open): no published price. Licence: d1 variants: LFM Open License v1.0 plus Apache-2.0 contributions (LvW-license-Snake-1.0); MiniMind-JEV: MIT; Laya Multilingual: Apache-2.0
- JAD-S1-7B-A1B v0.3 by DreamBlooms (open): no published price. Licence: Apache-2.0 adapter, code and base · Access: Public LoRA adapter and inference.py
- swiftpick-30B-A3B by harishvs (open): no published price. Licence: NVIDIA Open Model Agreement for the model derivative; code Apache-2.0 · Access: Public adapter and head; swiftpick-30B-A3B-v1-mm runtime tag
- Saif 4B v2 by GyrTechnology (open): no published price. Licence: CC BY-NC 4.0; non-commercial · Access: Public decision weights, runtime and Decision Index engine
- karpo-decision-31B by MachinePulseAI (open): no published price. Licence: MachinePulse Community License effective 12 Nov 2026. Earlier Apache-2.0 copies retain their rights; inference code is separately Apache-2.0
- JevStyle 2B by Chaoliang Yan (open): no published price. Licence: Apache-2.0; upstream data and teacher-output terms still apply · Access: Merged weights and custom runtime; separate text-only GGUF and MLX packages
- Laya spam classifiers by Nikita Kolmogorov (open): no published price. Licence: Apache-2.0, according to both model cards · Access: Public weights, question files and loading examples for both classifiers
- OneJev 31B by OmniJev (open): no published price. Licence: Apache-2.0, according to the card · Access: Merged safetensors and a Flide serving example
- Copernicus 31B / 57B by Poindexter Labs (open): no published price. Licence: Apache-2.0, according to the card · Access: Public 31B and 57B weights with separate reference serving code
- Scantron Preview by aidendle94 (open): no published price. Licence: LFM Open License v1.0 · Access: Weights, custom Transformers code, calibration, questions and edit provenance
- Kanana-2-v-decide by Kakao (open): no published price. Licence: Kanana Open License · Access: Public weights, custom Transformers code and /v1/systemone server
- Agastya Decision RAG 2B by Andra Labs (Amartya Sai Andra) (open): no published price. Licence: Apache-2.0 · Access: Public weights; Unsloth FastDecisionModel required for typed inference; hosted handler deployment untested
- termite-decide 0.8B by Tane Piper (open): no published price. Licence: Apache-2.0; 0.2 uses CC BY 4.0 tldr-pages text and project-written rows · Access: Public GGUF weights
- Qwen3.5-4B-Router-1M by Maziyar Panahi (open): no published price. Licence: Apache-2.0 · Access: Public adapter; Unsloth FastDecisionModel and base weights required
- Decisio 12B tuned v2 commit by tachara-ai (open): no published price. Licence: Apache-2.0, per card and included licence · Access: Public weight shards and decision_config.json
- Rein r1 family by jmc0 (open): no published price. Licence: Apache-2.0, per both cards · Access: Public merged backbone and decision-head weights
- Vev 4B v2 by Wang Xiaolong (open): no published price. Licence: CC BY-NC 4.0; Apache-2.0 base licence retained · Access: Public merged weights; no separate adapter
- Compliance Decisions 0.8B by souvickdascmsa019 (open): no published price. Licence: Apache-2.0 model tag; derived dataset CC BY 4.0 · Access: Public adapter and head; Unsloth required, standard PEFT alone omits the head
- JDI-Decision-V1 by JD Industrials (open): no published price. Licence: Apache-2.0 model tag; OCR components retain upstream terms · Access: Public weight shards, complete-system inference code and reproduction guide
- Jeva 4B by Qi Li and Xinchao Wang (NUS) (open): no published price. Licence: Apache-2.0 weights and decision head; base licence retained · Access: Public backbone, adapter and head.pt; use the Jeva project’s loading guidance
- RASD Laya track classifier by Galal Ban Amr (open): no published price. Licence: Apache-2.0 model card · Access: Public weights, question file and Laya loading example
- MoDe S / M / L by newrexlabs (open): no published price. Licence: Weights: FAIR Noncommercial Research License and Acceptable Use Policy; inference code: Apache-2.0 · Access: Public weights and MoDe inference package; custom model code requires trust_remote_code=True
- Laya Minecraft by Thomas Tesche (open): no published price. Licence: Apache-2.0 model card · Access: Public weights, question signatures and train_report.json; Laya runtime
- medgemma-decide-4b-v2 by Amaljith (open): no published price. Licence: Health AI Developer Foundations terms; derivative notice included · Access: Public merged weights, joint decision head, adapter, inference code and per-question temperatures
- medical-jev-4b by JuneYao (open): no published price. Licence: MIT code and adapter; Apache-2.0 base, with separate upstream data terms · Access: Public custom-format LoRA and inference bundle; not PEFT-compatible
- LingeeJevMulti-4B-v1 by Ashan0525 (open): no published price. Licence: Apache-2.0 · Access: Public weights, Python runtime and POST /v1/systemone
- Logits Sigma-1 / Duo by Logits (open): no published price. Licence: Apache-2.0 code and weights; training sources include share-alike, copyleft-labelled and possibly non-commercial data · Access: Public weights and Decision Index engines; one 96 GB GPU in the reported setups
- d1-2B RAG Verifier by landtml (open): no published price. Licence: LFM Open License v1.0 · Access: Merged BF16 weights, LoRA adapter, Q8_0 GGUF and scoring records
- LocHeal Verdict 2B by kinasr (open): no published price. Licence: LFM Open License v1.0 · Access: Merged BF16 weights, LoRA backup and custom Transformers code
- Amada by LiamDB (open): no published price. Licence: CC BY-NC-ND 4.0 for weights and repository code; non-commercial, no redistribution of modified versions · Access: Public release ZIP files and Python ONNX runner
- JevAlt by Mert Kaya (Eschatia Labs) (open): no published price. Licence: Apache-2.0 code and weights; dataset terms remain separate · Access: Full weights, Q4_K_M/Q5_K_M/Q8_0 GGUF, Transformers and llama.cpp server
- Rein-NPC-4B by jmc0 (open): no published price. Licence: Apache-2.0; licence file included · Access: BF16 weights, decision protocol and GGUF variants
- Laya Descent v4 by Eren Terakye (open): no published price. Licence: Apache-2.0; base licence and modification notice included · Access: PyTorch and MLX checkpoints, data and training report
- Chinese Decision Pointer 4B by quincyqiang / yanqiangmiffy (open): no published price. Licence: Apache-2.0 weights; source datasets retain their own terms, including non-commercial or research-only terms · Access: Merged model.safetensors with loading and evaluation code
- Aster-JEV-27B by k2021211255 (open): no published price. Licence: Fine-tuned weights CC BY-NC 4.0; original backbone Apache-2.0 · Access: BF16 backbone, FP32 stored head and single-A800 inference recipe
- Jevora 9B by kadirbekovvv / doxanocap (open): no published price. Licence: Apache-2.0 project code and derivative weights; upstream components and datasets retain their terms · Access: Pinned complete V1.6 package at revision 545549b8e8104f1780966ef1c13136abb32712b4; custom Python 3.13 loader
- Domyn-Edge-Jev-Decision by Mahesh Deshwal (open): no published price. Access: FP32 safetensors and custom Transformers code · Licence: Apache-2.0 declared in the card; no separate package licence file
- Clashbot d1-ft-joint-tac by Jyler (open): no published price. Access: FP16 weights and bundled custom loader; CPU loading uses FP32 · Licence: LFM Open License v1.0; file included
- QEV Compact by Ken Jo (open): no published price. Licence: Apache-2.0 files included; training datasets retain their own terms
- Julia 1 by Supersonic Labs (open): no published price. Access: Open weights and packaged Python inference code; private training pipeline · Licence: Apache-2.0 declared in the card; no separate package licence file
- Strands Decider 2B v1 by Strands Labs (open): no published price. Licence: Apache-2.0; LICENSE.md included
- ZeroPoint by Javier Marín (open): no published price. Access: Bundled model files; Python with NumPy, ONNX Runtime and tokenizers · Licence: Apache-2.0 code; upstream multilingual-e5-small is MIT, with notices
- MANTA by Gevaert Lab (open): no published price. Access: BF16 weights, custom Transformers code and a Python request wrapper · Licence: Apache-2.0 files included; source datasets retain their own terms
- N-Q-26M-JEV by Q Project (open): no published price. Access: Transformers custom code; safetensors and QPACK files · Licence: Q Project Model License 1.0: free non-commercial use; commercial use, including internal use, needs a paid licence. Company evaluation is allowed for up to 90 days without production or customer use.
- GameDecider by Holdout Labs (open): no published price. Licence: Apache-2.0; upstream Ettin-400M is MIT
- MNN-Pocket-0.3B-Dec by Taobao MNN (open): no published price. Access: Bundled Python runtime; CPU float32 or supported GPU dtypes · Licence: Apache-2.0 file included
- ARC 1.0 by Rayline (open): no published price. Access: Open weights and hosted arc-sage-1.0 / arc-swift-1.0; public vllm-arc plugin is unfinished · Licence: Apache-2.0; LICENSE and NOTICE included
- GS1 by BIGAI (open): no published price. Licence: Apache-2.0 code and weights; LICENSE and NOTICE included
- ANT by Semantique Team (open): no published price. Licence: Apache-2.0 for released heads; Qwen backbones retain their own Apache-2.0 licence
- decider-ja 0.5B by ken11 (open): no published price. Licence: MIT; LICENSE.md includes the base and Strands code attribution
- Ainvest Decision 31B v2.0 by Ainvest-World (open): no published price. Access: 16 BF16 weight shards, approximately 62.55 GB before runtime overhead; CUDA package and CLI · Licence: Apache-2.0 release; retain base-model and MIT helper notices
- newTokenEra decision 27B by NewTokenEra (open): no published price. Access: 18 BF16 weight shards, about 52.17 GB before runtime overhead; custom Transformers code with trust_remote_code · Licence: Apache-2.0; actual LICENSE included
- ProbeLoop Laya stated limits by submsk (open): no published price. Licence: Apache-2.0 fine-tuning and exports; retain Laya and mmBERT upstream attribution
- femto-jev by igorktech (open): no published price. Access: Public weights and single-file Python inference; no text generation · Licence: Apache-2.0, with upstream notices
- Laya medical specialty by AI Anytime (open): no published price. Access: Public backbone and decision-head safetensors; load or serve with Snapcall · Licence: Apache-2.0 according to the card; dataset terms remain separate
Tooling
- Ollama v0.35 by Ollama (tooling): no published price
- prismhq/jev-router by prismhq (tooling): no published price
- mizorewww/laya-mlx by mizorewww (tooling): no published price. Licence: Apache-2.0
Community
- SemIf (formerly OpenJev) by TheoLeeCJ (community): no published price
- bnsd55/jevmlx by bnsd55 (community): no published price
- kw2828/OpenJev by kw2828 (community): no published price
- akash-kamat/system-one-gemma by akash-kamat (community): no published price
- leofmarciano/groot by leofmarciano (community): no published price. Licence: Apache-2.0
- jwuthri-cloud/SelfJev by jwuthri-cloud (community): no published price. Licence: Apache-2.0 (code)
- SecJev-4B Spot2 V3 by macmacmacmac (community): no published price. Licence: SecJev Use and Distribution Agreement v1.0; custom terms
- CodeSync Knack by DevsHub (community): no published price. Access: CodeSync bundle; standalone Ollama runner and GGUF files · Licence: Not specified in the card or file inventory