Decision interfaces without trained weights — use your own LLMs as classifiers.
These are NOT models. They extract decisions from existing LLMs via constrained decoding, logit readout, or wrapper APIs. No trained decision weights — the decision capability comes from inference-time techniques on frozen base models.
Looking for trained decision models? See the Model catalog.
bandr.ai (bandr-ai)
Recipe in the Bandits toolkit that LoRA-tunes Qwen3.5-4B-Base into a per-step agent-trace judge on your own labels. No checkpoint, no license, no inference server.
Why not a model
Ships a training recipe, not a model: LoRA on Qwen3.5-4B-Base, local training UI, scorecard vs Jev via /v1/systemone. No released weights, no license.
classifier.dev
HTTP/CLI/MCP wrapper over hosted Jev with smart escalation to reasoning LLMs for uncertain cases.
Why not a model
Hosted wrapper over Jev API — not a separate model, just a convenience layer.
Cua AI
Lightweight specialist (~706k params) for scoring form field actions: use, check, click, skip.
Why not a model
Narrow-task specialist for form field actions — not a general-purpose System One decision model.
notnotsamuel
Research method for parallel constrained scoring on frozen LiquidAI LFM2.5-350M weights.
Why not a model
Parallel constrained scoring on unchanged LiquidAI weights — name 'RLCD' ≠ TypeSafe RLCD training method.
zhengxuyu
Lightweight method that wraps Qwen checkpoints to serve TypeSafe-compatible decisions locally.
Why not a model
Wraps off-the-shelf Qwen checkpoints as Jev-schema decisions — probabilities are uncalibrated by default.
Ollama
Ollama v0.35+ adds a native, TypeSafe-compatible /v1/systemone endpoint and three decision models: nimble, tev1 and tev1:0.8b. Local only for now.
Why not a model
Inference server. Since v0.35 it serves decision models trained by others (Nimble, Tev1) on a local /v1/systemone endpoint; it has no decision weights of its own.
ollaya-dev
Ollama for decision models: pull and serve open decision models locally behind a TypeSafe-compatible API.
Why not a model
Serves existing open decision models locally (Laya, Decider, NLI, GLiClass, Kev, Von); no trained weights of its own — it's distribution and inference infra.
ikermoel (Iker Moel Tacher)
Python library (import so1) that packs several typed questions into one forward pass of a stock open LLM and reads option-letter logits. HF Transformers and vLLM backends.
Why not a model
Reads option-letter logits from stock open LLMs (Qwen) in one packed forward pass. No decision training; calibration is an optional temperature you fit yourself.
OpenAI
Limited-preview OpenAI API that points GPT-6 Luna at your own questions with a fixed set of answers (text or image context). Not the same product as OpenRouter's Decisions API.
Why not a model
No dedicated decision weights documented. OpenAI serves it on a version of GPT-6 Luna and it returns "a selection"; no public docs, schema or pricing yet. Re-check at broad release.
ekzhang
SGLang-based runtime providing TypeSafe-compatible /v1/systemone endpoint over Qwen3.6-35B-A3B.
Why not a model
TypeSafe-compatible endpoint over Qwen via SGLang prefill/logprob hack — not a trained decision model.
alperiox
Audio-native Jev-shaped decisions without ASR text decode — processes audio directly.
Why not a model
Audio modality specialist — not a text-based System One peer; different input domain entirely.
TheoLeeCJ
Browser-first runtime that extracts typed decisions from frozen open LLMs via WebGPU/wllama.
Why not a model
Reads typed option logits from frozen open LMs — no trained decision weights, just inference-time logit extraction.
Featherless AI
Featherless stack that converts any open LLM into a typed decision classifier via next-token logits.
Why not a model
Turns any compatible open LM into a typed classifier via next-token logits — no fine-tuning required.
TypeLLM
SGLang-based runtime for type-safe generation on autoregressive LLMs, with thinking mode and image input. Open source, and since 29 Sep 2026 also a hosted playground and API.
Why not a model
Constrained decoding layer over existing autoregressive LLMs — does not change architecture or weights.
mode-io
Native vLLM (Linux) and Apple Silicon serving for open Jev-style decision checkpoints: Choice/Noul/Score over HTTP /v1/systemone, including Valen multimodal.
Why not a model
Serving engine for existing Jev-style checkpoints (vLLM on Linux, MLX/MPS on Mac). No decision training — it selects a protocol and runs inference.
