# Jev alternatives with hosted and open models

> Jev alternatives span 59 other registry entries, including hosted models and open weights. Each entry links its sources and published prices.

Updated 2026-11-04 (Australia/Adelaide)

[Compare decision models](<https://decisionmodels.ai/compare>)

The registry supplies each summary and Price fact. Capability descriptions and prices are vendor-reported; model pages link labelled evidence. Community projects and tools have their own registry groups, separate from open weights.

## Jev

- [Jev](<https://decisionmodels.ai/models/jev>) by TypeSafe AI: A hosted API: send your app's state plus typed questions (Choice, Score or Noul) and get a probability back for each answer. Price (VENDOR-REPORTED): $0.042 per million input tokens; output free
  - [Source: Announcement](<https://typesafe.ai/blog/introducing-system-one-models-and-jev>)
  - [Source: Jev 1.14](<https://typesafe.ai/blog/jev-1-14>)
  - [Source: Docs](<https://docs.typesafe.ai>)
  - [Source: On OpenRouter](<https://openrouter.ai/docs/guides/community/jev>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

## Hosted

- [Decisions API](<https://decisionmodels.ai/models/openai-decisions>) by OpenAI: OpenAI's [Decisions API](<https://decisionmodels.ai/models/openai-decisions>) uses GPT-6 Luna to return typed answers for classification, routing and agent actions. Price (VENDOR-REPORTED): $0.10 per million uncached input tokens; output free
  - [Source: Decisions guide](<https://developers.openai.com/api/docs/guides/decisions>)
  - [Source: API changelog](<https://developers.openai.com/api/docs/changelog>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [d1](<https://decisionmodels.ai/models/d1>) by Liquid AI: Liquid AI's decision model family. Price (VENDOR-REPORTED): 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)
  - [Source: Docs](<https://docs.liquid.ai/lfm/models/decision-models>)
  - [Source: Announcement](<https://x.com/liquidai/status/2105003472332693869>)
  - [Source: Decision Index](<https://huggingface.co/spaces/multimodalart/jev-decision-index>)
  - [Source: Open d1 release](<https://huggingface.co/blog/LiquidAI/open-d1>)
  - [Source: d1.1 on OpenRouter](<https://openrouter.ai/liquid/d1.1>)
  - [Source: d1-2B](<https://huggingface.co/LiquidAI/d1-2B>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Mercury Decide](<https://decisionmodels.ai/models/mercury-decide>) by Inception: Inception's decision model, served as a System One endpoint: send state and typed questions, get a choice, a score or a yes/no answer, each with a probability. Price (VENDOR-REPORTED): $0.02 per million input tokens at a 50% discount, output free; a free tier remains (OpenRouter, as of 22 Oct 2026)
  - [Source: OpenRouter](<https://openrouter.ai/inception/mercury-decide:free>)
  - [Source: Announcement](<https://x.com/_inception_ai/status/2105375133003325768>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Solar Decide](<https://decisionmodels.ai/models/solar-decide>) by Upstage: Upstage's decision endpoint, available through OpenRouter. Price (VENDOR-REPORTED): OpenRouter lists $0.05 per million input tokens, output $0 (as of 2 Oct 2026); the launch post described a limited-time 50% discount
  - [Source: OpenRouter](<https://openrouter.ai/compare/upstage/solar-decide>)
  - [Source: OpenRouter announcement](<https://x.com/OpenRouter/status/2104625184703742225>)
  - [Source: Solar Decide Flash](<https://openrouter.ai/upstage/solar-decide-flash>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Span-01](<https://decisionmodels.ai/models/span-01>) by Respan: A one-pass classifier for agent traces. Price (VENDOR-REPORTED): $0.02 per million input tokens; output free
  - [Source: Announcement](<https://respan.ai/blog/introducing-span-1>)
  - [Source: Span-02](<https://www.respan.ai/blog/introducing-span-2>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Decider 1](<https://decisionmodels.ai/models/decider-1>) by meraGPT: A hosted decision model served only at /v1/systemone, the request format TypeSafe's SDK speaks. Price (VENDOR-REPORTED): $0.03 per million input tokens; output $0
  - [Source: meragpt.com](<https://meragpt.com/>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Microsoft-Decision-1](<https://decisionmodels.ai/models/microsoft-decision-1>) by Microsoft: Microsoft's decision-scoring model for routing, classification, prioritisation, verification and workflow control. Price (VENDOR-REPORTED): $0.042 per million input tokens; output free
  - [Source: Announcement](<https://commandline.microsoft.com/microsoft-decision-1-model-foundry/>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Clef-omni](<https://decisionmodels.ai/models/clef-omni>) by Cloudflare: The [Clef](<https://decisionmodels.ai/models/clef-omni>) family on Workers AI answers typed questions in one pass. Price (VENDOR-REPORTED): $0.150 per million input tokens
  - [Source: Cloudflare changelog](<https://developers.cloudflare.com/changelog/post/2026-10-09-clef-omni-workers-ai/>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Snowflake Decision](<https://decisionmodels.ai/models/snowflake-decision>) by Snowflake: A decision model you call from SQL.
  - [Source: Announcement](<https://www.snowflake.com/en/blog/snowflake-decision-cortex-ai-functions/>)
  - [Source: Decision Fast](<https://www.snowflake.com/en/blog/snowflake-decision-fast-low-latency-ai-decisions/>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Celeris-1-decision](<https://decisionmodels.ai/models/celeris-1>) by Celeris: A closed decision model for text, structured data and images that can give a one-sentence reason alongside each probability. Price (VENDOR-REPORTED): $0.04 per million input tokens; output free
  - [Source: Announcement](<https://celeris.ai/celeris-1-decision>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [SubQ Snap](<https://decisionmodels.ai/models/subq-snap>) by Subquadratic: A long-context decision model for text and images, with a 384K-token window. Price (VENDOR-REPORTED): $0.04 per million input tokens; output free
  - [Source: Announcement](<https://subq.ai/introducing-subq-snap>)
  - [Source: Version 1.1 release](<https://subq.ai/subq-snap-1-1>)
  - [Source: Baseten](<https://www.baseten.co/library/subq-snap-11/>)
  - [Source: API models, status and pricing](<https://docs.subq.ai/using-the-api/models/>)
  - [Source: Baseten launch, 02 Nov 2026](<https://x.com/baseten/status/2117356128631976142>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Classify-1](<https://decisionmodels.ai/models/classify-1>) by ScaleDown: Scores text or a whole document against your own choice, yes/no and ordered-scale questions.
  - [Source: Docs](<https://docs.scaledown.ai/api-reference/decisions-overview>)
  - [Source: OpenRouter](<https://openrouter.ai/scaledown/classify-1>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Clairic](<https://decisionmodels.ai/models/clairic>) by Cloudflare: A new branch of the family: a System One extraction model. Price (VENDOR-REPORTED): $0.10 per million input tokens on OpenRouter; output free
  - [Source: Announcement](<https://blog.cloudflare.com/clairic-extraction-model/>)
  - [Source: OpenRouter listing](<https://openrouter.ai/cloudflare/clairic>)
  - [Source: OpenRouter decisions inventory (34 entries, checked 4 Nov 2026)](<https://openrouter.ai/api/v1/models?output_modalities=decisions>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Parallel Decisions API](<https://decisionmodels.ai/models/parallel-decisions>) by Parallel: A decision engine that searches the live web before it answers. Price (VENDOR-REPORTED): $1 per 1,000 calls (as of 25 Oct 2026)
  - [Source: Announcement](<https://parallel.ai/blog/decisions-api>)
  - [Source: Docs](<https://docs.parallel.ai/decisions/decisions-quickstart>)
  - [Source: Benchmark](<https://github.com/parallel-web/pws-decisions-benchmark>)
  - [Source: Benchmark announcement](<https://parallel.ai/blog/pws-decisions-benchmark>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Hume Audio Decisions API](<https://decisionmodels.ai/models/hume-audio-decisions>) by Hume AI: Hume's hosted model answers questions about speech and sound with probabilities. Price (VENDOR-REPORTED): $0.47 per million input tokens (audio, questions and context); answers not billed. Hume's billing docs, checked 03 Nov 2026
  - [Source: Announcement](<https://www.hume.ai/blog/introducing-hume-audio-decision-api>)
  - [Source: Product and playground](<https://www.hume.ai/products/decision-model-api>)
  - [Source: Docs](<https://dev.hume.ai/audio-decisions/docs/overview>)
  - [Source: Billing](<https://dev.hume.ai/audio-decisions/docs/billing>)
  - [Source: Audio preparation](<https://dev.hume.ai/audio-decisions/docs/preparing-your-audio>)
  - [Source: Launch changelog](<https://dev.hume.ai/audio-decisions/changelog/2026/11/2.md>)
  - [Source: Python SDK](<https://github.com/HumeAI/hume-audio-decisions-python-sdk>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Zoom Decisions API](<https://decisionmodels.ai/models/zoom-decisions>) by Zoom: [Zoom](<https://decisionmodels.ai/models/zoom-decisions>)'s hosted [Decisions API](<https://decisionmodels.ai/models/zoom-decisions>) and [Decisions API Pro](<https://decisionmodels.ai/models/zoom-decisions>) accept text, images or both. Price (VENDOR-REPORTED): $0.042 per million tokens for Decisions API; $0.10 for Pro, per Zoom's product page checked 03 Nov 2026
  - [Source: Product, playground and pricing](<https://www.zoom.com/en/products/ai-services/decisions-api/>)
  - [Source: Launch changelog](<https://developers.zoom.us/changelog/ai-services/october-19-2026/>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [LingDT-Decision-1.0](<https://decisionmodels.ai/models/lingdt-decision>) by Ant Digital Technologies (蚂蚁数科): Ant Digital Technologies' System One model for choosing answers to business questions, including native multi-select and decisions ordered by dependencies. Price (VENDOR-REPORTED): 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.
  - [Source: DTMaaS model page](<https://maas.antdigital.com/models/modelservice-1792325631780001741>)
  - [Source: Official model data and API example](<https://maas.antdigital.com/api/v1/model-service/public/get/modelservice-1792325631780001741>)
  - [Source: API guide](<https://maas.antdigital.com/docs/lingdt-decision-api-guide>)
  - [Source: Launch report (IT之家)](<https://www.ithome.com/1/016/633.htm>)
  - [Source: Jev pricing source](<https://docs.typesafe.ai/models>)
  - [Source: Microsoft-Decision-1 source](<https://commandline.microsoft.com/microsoft-decision-1-model-foundry/>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

## Open weights

- [Kev](<https://decisionmodels.ai/models/kev>) by Jared Palmer: [Kev](<https://decisionmodels.ai/models/kev>) is Jared Palmer's family of open, Jev-compatible decision models, from 0.8B to 27B parameters. Price (VENDOR-REPORTED): $0.042 per million input tokens and $0 per million output tokens for jaredpalmer/kev-4b on OpenRouter (VENDOR-REPORTED, 2 Nov 2026)
  - [Source: GitHub](<https://github.com/jaredpalmer/kev>)
  - [Source: Kev 1.0 release](<https://github.com/jaredpalmer/kev/releases/tag/kev-1.0>)
  - [Source: Hugging Face](<https://huggingface.co/jaredpalmer>)
  - [Source: Kev 4B on OpenRouter](<https://openrouter.ai/jaredpalmer/kev-4b>)
  - [Source: GitHub API: stars](<https://api.github.com/repos/jaredpalmer/kev>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [DecisionTune 1.0](<https://decisionmodels.ai/models/decisiontune>) by DecisionTune: A local decision model built on ModernBERT-large: give it a state, a question and options, and it returns a probability for each option in one encoder pass.
  - [Source: Hugging Face](<https://huggingface.co/decision-tune/decisiontune-1.0>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Tev1-4B](<https://decisionmodels.ai/models/tev1>) by Together AI: Together's Jev-inspired experiment: a Qwen3.5-4B fine-tune that reads a state, a question and 2 to 24 lettered options.
  - [Source: Hugging Face](<https://huggingface.co/togethercomputer/Tev1-4B-experimental>)
  - [Source: GitHub](<https://github.com/togethercomputer/tev1>)
  - [Source: Announcement](<https://x.com/togethercompute/status/2102882216950763814>)
  - [Source: Untuned 4B baseline test](<https://github.com/Joshhuang123/jev-rsi>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [GLiNER2.5-Decide](<https://decisionmodels.ai/models/gliner25-decide>) by Fastino: A 340M-parameter encoder decision model from the team behind GLiNER, fine-tuned from GLiNER2.
  - [Source: Announcement](<https://fastino.ai/blog/gliner-2-5-decide-open-weight-decision-model>)
  - [Source: Hugging Face](<https://huggingface.co/fastino/GLiNER2.5-Decide>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Laya](<https://decisionmodels.ai/models/laya>) by Convai Innovations: A non-autoregressive decision engine on ModernBERT-large (421M), with a 322M multilingual sibling.
  - [Source: Site](<https://laya.convaiinnovations.com>)
  - [Source: GitHub](<https://github.com/NandhaKishorM/laya>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Nimble](<https://decisionmodels.ai/models/nimble>) by Bespoke Labs: A 9B decision model, LoRA-tuned from Qwen3.5-9B, with its 2,676 training examples published.
  - [Source: GitHub](<https://github.com/bespokelabsai/nimble>)
  - [Source: Ollama](<https://ollama.com/library/nimble>)
  - [Source: Hugging Face](<https://huggingface.co/bespokelabs/Bespoke-Nimble-9B>)
  - [Source: Nimble README](<https://github.com/bespokelabsai/nimble>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Decision 1.0](<https://decisionmodels.ai/models/decision-1>) by vLLM Semantic Router: Open decision models from the vLLM Semantic Router project, published as "[Decision 1.0](<https://decisionmodels.ai/models/decision-1>): towards open decision foundation models".
  - [Source: Hugging Face](<https://huggingface.co/collections/llm-semantic-router/decision-10-6ab12177bd0002394d8409f9>)
  - [Source: Announcement PR](<https://github.com/vllm-project/semantic-router/pull/4041>)
  - [Source: d3 on Hugging Face](<https://huggingface.co/vllm-sr/d3>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Decider](<https://decisionmodels.ai/models/pplx-decider>) by Perplexity: Perplexity's decision model reads text and images and returns a probability for every answer. Price (VENDOR-REPORTED): $0.02 (V1.2) and $0.01 (Flash) per million input tokens on OpenRouter, output free (as of 22 Oct 2026)
  - [Source: V1.2 announcement](<https://community.perplexity.ai/t/pplx-decider-v1-2-is-the-highest-scoring-decision-model-on-claimbench/6392>)
  - [Source: Hugging Face](<https://huggingface.co/perplexity-ai/pplx-decider-v1.2>)
  - [Source: V1.1 announcement](<https://community.perplexity.ai/t/pplx-decider-v1-1-27b-our-updated-open-weights-multimodal-decision-model-is-now-available/6286>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Drex 2.0](<https://decisionmodels.ai/models/drex>) by Nace.AI: [Drex 2.0](<https://decisionmodels.ai/models/drex>) returns probabilities over typed answers for text, with open weights under Nace.AI's Open RAIL licence. Price (VENDOR-REPORTED): $0.06 per million input tokens for Drex 2.0; $0.03 for Drex Max, Max v1.1 and Max Finance, hosted
  - [Source: Model table](<https://console.nace.ai/docs/drex/reference/models>)
  - [Source: Hugging Face](<https://huggingface.co/nace-ai/drex-v2.0>)
  - [Source: Drex Max weights and local inference](<https://huggingface.co/nace-ai/drex-max-v1>)
  - [Source: Drex Max Finance API guide](<https://console.nace.ai/docs/drex/guides/drex-max#drex-max-finance>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [H2O-Lightning-4B](<https://decisionmodels.ai/models/h2o-lightning>) by H2O.ai: A 4B open model built on Qwen3.5-4B that runs on unmodified vLLM.
  - [Source: Announcement](<https://h2o.ai/blog/2026/h2o-lightning-jevbench>)
  - [Source: Hugging Face](<https://huggingface.co/h2oai/h2o-lightning-4b>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Jebadiah v2.1](<https://decisionmodels.ai/models/jebadiah>) by frontier-infra: Open decision models that read option-label probabilities in a single pass with thinking switched off: you get a pick and a confidence, not an essay.
  - [Source: Release post](<https://huggingface.co/blog/frontier-infra/jebadiah-v2-1>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Lumma-Fev-27B](<https://decisionmodels.ai/models/lumma-fev>) by FrontiersMind: A 27B open decision model that answers in English, Hindi, Tamil and Kannada.
  - [Source: Release post](<https://huggingface.co/blog/FrontiersMind/lumma-fev-27b>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Granite Switch 4.1](<https://decisionmodels.ai/models/granite-switch>) by IBM: IBM's switchable models do chat, decisions and speech-to-text from one endpoint. 4.1 adds a general-purpose Decision adapter that speaks the /v1/systemone interface.
  - [Source: Announcement](<https://huggingface.co/blog/ibm-granite/granite-switch-4-1>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [TYGER](<https://decisionmodels.ai/models/tyger>) by NineNineSix: A decision model for speech.
  - [Source: Hugging Face](<https://huggingface.co/nineninesix/tyger>)
  - [Source: Announcement](<https://x.com/defoemark/status/2111306095591670263>)
  - [Source: Voice agent](<https://github.com/nineninesix-ai/tyger-s2s>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Talos](<https://decisionmodels.ai/models/talos>) by Tractian: A decision model that stands between AI agents and the controllers that run factories.
  - [Source: GitHub](<https://github.com/tractian/talos>)
  - [Source: Hugging Face](<https://huggingface.co/tractian/talos-0.8b>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Mammoth 1](<https://decisionmodels.ai/models/baseten-mammoth>) by Baseten (Base Labs): Two open decision models from Base Labs, Baseten's research team: [mammoth-1](<https://decisionmodels.ai/models/baseten-mammoth>) (27B) and elephant-1 (9B), post-trained from Qwen3.5. Price (VENDOR-REPORTED): 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)
  - [Source: Announcement](<https://www.baseten.co/blog/the-best-decision-models-in-the-world-mammoth-1-and-elephant-1/>)
  - [Source: Technical report](<https://labs.baseten.co/articles/mammoth-1-and-elephant-1-frontier-decision-models>)
  - [Source: mammoth-1 on Hugging Face](<https://huggingface.co/baselabs/mammoth-1>)
  - [Source: elephant-1 on Hugging Face](<https://huggingface.co/baselabs/elephant-1>)
  - [Source: joey-1](<https://huggingface.co/baselabs/joey-1>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Qev 0.8B](<https://decisionmodels.ai/models/qev>) by labqoat: A tiny open decision model that runs locally, built on Qwen3.5-0.8B and reading text and images.
  - [Source: Model page](<https://app.labqoat.com/e/qev/qev/>)
  - [Source: Hugging Face](<https://huggingface.co/labqoat/qev-0.8b>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Decido](<https://decisionmodels.ai/models/decido>) by decido-ai: An open decision model built to run on a laptop CPU: a LoRA fine-tune of Gemma 4 26B-A4B shipped as an 8-bit GGUF for llama.cpp, answering in the same wire format as [Jev](<https://decisionmodels.ai/models/jev>)'s System One API.
  - [Source: Hugging Face](<https://huggingface.co/decido-ai/decido-26b-a4b>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Arc-decide](<https://decisionmodels.ai/models/arc-decide>) by Arc53 (DocsGPT): The small decision model inside DocsGPT, used for quick judgements such as whether a message is a prompt injection or whether a chunk answers the question.
  - [Source: Docs](<https://docs.docsgpt.cloud/Models/decision-model>)
  - [Source: Hugging Face](<https://huggingface.co/Arc53/arc-decide-0.4b-v0.2>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Valen](<https://decisionmodels.ai/models/valen>) by Valen Team: Open decision models in three sizes that read text, images and video, built on Qwen3.5.
  - [Source: Site and demo](<https://valen-team.github.io/>)
  - [Source: Hugging Face](<https://huggingface.co/Valen-Team/Valen-4B>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Fovea-4B](<https://decisionmodels.ai/models/fovea>) by Sivasuthan: An open decision model for images: give it a photo, document, receipt, chart or screenshot plus a typed question and it returns a probability for every allowed answer, served over [Jev](<https://decisionmodels.ai/models/jev>)'s System One API.
  - [Source: GitHub](<https://github.com/Sivasuthan9/fovea>)
  - [Source: Hugging Face](<https://huggingface.co/Sivasuthan/fovea-4b>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [homi](<https://decisionmodels.ai/models/homi>) by egma-ai: An open decision model that listens instead of reading: give it an audio clip and a typed question (how does the speaker feel? does the pitch rise?) and it returns a probability for every option, without a transcript.
  - [Source: GitHub](<https://github.com/egma-ai/homi>)
  - [Source: Hugging Face](<https://huggingface.co/egma-ai/homi>)
  - [Source: Show HN](<https://news.ycombinator.com/item?id=50276913>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Nimbus](<https://decisionmodels.ai/models/nimbus>) by Crele: A decision model for live audio.
  - [Source: GitHub](<https://github.com/Crele-AI/nimbus>)
  - [Source: Hugging Face](<https://huggingface.co/crele/nimbus-v1>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [GLiDE](<https://decisionmodels.ai/models/glide>) by Fastino: Fastino's big decision model, built on Qwen3.8-27B: give it text, JSON or images plus typed questions and it returns a probability for every option, with nothing generated.
  - [Source: Hugging Face](<https://huggingface.co/fastino/GLiDE>)
  - [Source: API docs](<https://docs.fastino.ai/inference/systemone>)
  - [Source: Decision Index](<https://huggingface.co/spaces/multimodalart/jev-decision-index>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [UltraBERT Curation](<https://decisionmodels.ai/models/ultrabert-curation>) by Daniel van Strien: A 380M-parameter decision model for data curation: give it a web page, prompt, maths problem or library record and typed questions (topic, format, educational value, difficulty) and it returns a probability for every option.
  - [Source: Hugging Face](<https://huggingface.co/davanstrien/ultrabert-380m-curation>)
  - [Source: Recipe](<https://github.com/davanstrien/curation-decision-recipe>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [KnowLine](<https://decisionmodels.ai/models/knowline>) by PelaAI: A fast-moving family of open decision models from PelaAI, trained in an agent-driven data loop, with English and Chinese in mind: from 0.8B up to 35B-A3B, with new generations posted every few days.
  - [Source: Hugging Face](<https://huggingface.co/PelaAI/KnowLine-31B-Gen1>)
  - [Source: Decision Index](<https://huggingface.co/spaces/multimodalart/jev-decision-index>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Ru-Jev](<https://decisionmodels.ai/models/ru-jev>) by besktech (beskvladimir-create): A Russian-first typed-decision model built on mmBERT-base (307M), with a separate scoring head.
  - [Source: Weights and v1.1 model card](<https://huggingface.co/besktech/ru-jev>)
  - [Source: GitHub](<https://github.com/beskvladimir-create/ru-jev>)
  - [Source: Release metadata](<https://huggingface.co/api/models/besktech/ru-jev>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Intern-Decision](<https://decisionmodels.ai/models/intern-decision>) by InternLM: Send a shared state, named questions and optional images to these multimodal models.
  - [Source: 4B weights and model card](<https://huggingface.co/internlm/Intern-Decision-4B>)
  - [Source: GitHub](<https://github.com/internlm/Intern-Decision>)
  - [Source: Report](<https://arxiv.org/abs/2610.22131>)
  - [Source: Hugging Face upload metadata](<https://huggingface.co/api/models/internlm/Intern-Decision-4B>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [MiniCPM-OCR Jev](<https://decisionmodels.ai/models/minicpm-ocr-jev>) by OpenBMB: This 2B specialist scores whether a candidate OCR reading matches a document region.
  - [Source: Weights and model card](<https://huggingface.co/openbmb/MiniCPM-OCR-Jev>)
  - [Source: Code and deployment](<https://github.com/OpenBMB/MiniCPM-OCR>)
  - [Source: JevOCRBench](<https://huggingface.co/datasets/openbmb/JevOCRBench>)
  - [Source: Hugging Face upload metadata](<https://huggingface.co/api/models/openbmb/MiniCPM-OCR-Jev>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [hs-decide-1-flash](<https://decisionmodels.ai/models/hs-decide-1-flash>) by Vectorize (Hindsight): Vectorize's Hindsight team fine-tuned this 0.8B model from Qwen3.5-0.8B for agent memory. Price (VENDOR-REPORTED): $0.02 per million input tokens on Hindsight Inference; input only
  - [Source: Launch and evaluation](<https://hindsight.vectorize.io/blog/2026/11/03/hindsight-models>)
  - [Source: Weights and model card](<https://huggingface.co/hindsight-ai/hs-decide-1-flash>)
  - [Source: Hindsight code](<https://github.com/vectorize-io/hindsight>)
  - [Source: System evaluation](<https://benchmarks.hindsight.vectorize.io>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [Smaug-Decisions](<https://decisionmodels.ai/models/smaug-decisions>) by Abacus.AI: Abacus.AI's 4B decision model answers a typed question about audio, an image or text with a probability per option in one pass.
  - [Source: Weights and model card](<https://huggingface.co/abacusai/Smaug-Decisions>)
  - [Source: 0.7B audio tier](<https://huggingface.co/abacusai/Smaug-Audio-Decisions-0.7B>)
  - [Source: LiteRT build](<https://huggingface.co/abacusai/Smaug-Decisions-LiteRT>)
  - [Source: Maker blog announcement](<https://blog.abacus.ai/blog/2026/11/02/smaug-decisions/>)
  - [Source: X announcement: 3 Nov 2026](<https://x.com/bindureddy/status/2117659234448154646>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [REAX 1.3](<https://decisionmodels.ai/models/reax>) by REAX: [REAX 1.3](<https://decisionmodels.ai/models/reax>) runs two model parts on one GPU and averages their per-option probabilities 50/50.
  - [Source: Weights, results and upstream notices](<https://huggingface.co/decisionmodels/REAX-1.3>)
  - [Source: REAX Engine](<https://github.com/reaxlabs/reax-engine>)
  - [Source: Announcement](<https://x.com/reaxlabs/status/2117664350655729995>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [K-Decision-9B](<https://decisionmodels.ai/models/k-decision>) by ONYULTEA: A Korean-specialised 9B decision model based on Qwen3.5-9B, trained with int8 LoRA at rank 32.
  - [Source: Weights, licence declaration and results](<https://huggingface.co/ONYULTEA/K-Decision-9B>)
  - [Source: Serving and evaluation code](<https://github.com/onyultea/k-decision>)
  - [Source: Weight file inventory](<https://huggingface.co/api/models/ONYULTEA/K-Decision-9B/tree/main>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

## Tooling

- [Ollama v0.35](<https://decisionmodels.ai/models/ollama>) by Ollama: Ollama added native decision models through /v1/systemone, based on TypeSafe's [Jev](<https://decisionmodels.ai/models/jev>) API, so you can run one on your own machine.
  - [Source: Release notes](<https://github.com/ollama/ollama/releases/tag/v0.35.0>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [prismhq/jev-router](<https://decisionmodels.ai/models/jev-router>) by prismhq: A LiteLLM-based router with an optional [Jev](<https://decisionmodels.ai/models/jev>) decision backend: when a TypeSafe API key is configured it can use [Jev](<https://decisionmodels.ai/models/jev>) to pick a model per request, and otherwise falls back to its own rules-based [decider](<https://decisionmodels.ai/models/pplx-decider>).
  - [Source: GitHub](<https://github.com/prismhq/jev-router>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [mizorewww/laya-mlx](<https://decisionmodels.ai/models/laya-mlx>) by mizorewww: Runs the open [Laya](<https://decisionmodels.ai/models/laya>) decision models natively on Apple Silicon with MLX: no PyTorch, no cloud API, zero output tokens.
  - [Source: GitHub](<https://github.com/mizorewww/laya-mlx>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

## Community

- [SemIf (formerly OpenJev)](<https://decisionmodels.ai/models/openjev>) by TheoLeeCJ: Reproduces [Jev](<https://decisionmodels.ai/models/jev>)'s interface pattern with open models: it reads typed option probabilities directly from a model, with no answer sentence and no decoding loop.
  - [Source: openjev.com](<https://openjev.com/>)
  - [Source: TheoLeeCJ/SemIf-OpenJev](<https://github.com/TheoLeeCJ/SemIf-OpenJev>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [bnsd55/jevmlx](<https://decisionmodels.ai/models/bnsd55-openjev>) by bnsd55: Parallel constrained decisions for local models through mlx-lm on Apple Silicon: the schema is a set of typed fields, the context is prefilled once and broadcast across one batch row per field.
  - [Source: GitHub](<https://github.com/bnsd55/jevmlx>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [kw2828/OpenJev](<https://decisionmodels.ai/models/kw2828-openjev>) by kw2828: A browser and local playground for decision experiments on memory, uncertainty and control, using Qwen-family models and returning option probabilities.
  - [Source: GitHub](<https://github.com/kw2828/OpenJev>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [akash-kamat/system-one-gemma](<https://decisionmodels.ai/models/system-one-gemma>) by akash-kamat: Gemma 3 270M with a scoring head, producing a decision in a single forward pass with no text generation.
  - [Source: GitHub](<https://github.com/akash-kamat/system-one-gemma>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [leofmarciano/groot](<https://decisionmodels.ai/models/groot>) by leofmarciano: Groot 1 S, a 149M-parameter open typed-decision model that speaks the System One request format and reads states of up to 64k tokens in the maker's tests.
  - [Source: GitHub](<https://github.com/leofmarciano/groot>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

- [jwuthri-cloud/SelfJev](<https://decisionmodels.ai/models/selfjev>) by jwuthri-cloud: A self-hosted decision model with a Jev-compatible API: you run the server on your own GPU, and a 230 MB vision adapter on Qwen3.5-4B reads text and images.
  - [Source: GitHub](<https://github.com/jwuthri-cloud/SelfJev>)
  - [Source: Hugging Face](<https://huggingface.co/Jwuthrich/selfjev-4b-vision>)
  [Compare prices](<https://decisionmodels.ai/pricing>)

[Compare JevBench scores](<https://decisionmodels.ai/jevbench>)

[What is a decision model?](<https://decisionmodels.ai/what-is-a-decision-model>)