Last verified 2026-10-15
All agent & decision APIs
Source-linked pricing, limits, and status for 20 APIs. Prefer the interactive home to filter; this page is the full index.
- OpenAI Decisions API — OpenAI · Decision model
Dedicated POST /v1/decisions endpoint that returns typed answers (probability, choice, or score) about text and images instead of generated text. Model: gpt-6-luna (only model available). - Microsoft-Decision-1 — Microsoft (Foundry) · Decision model
Small decision model in Microsoft Foundry that returns typed numeric decisions (noul / choice / score) about text or JSON state. No free-form output or rationale. - Vercel AI Gateway — Decisions endpoint — Vercel · Gateway / proxy
OpenAI-compatible POST /decisions endpoint on Vercel AI Gateway that routes to any decision model on the gateway (e.g. openai/gpt-6-luna-decisions, typesafe-ai/jev). - Jev (TypeSafe AI) — TypeSafe AI · Decision model
Hosted "System One" decision model from TypeSafe AI: send a state plus typed questions (noul, choice, score) to POST /v1/systemone and get probabilities back. jev-latest points to the stable jev-1.13.0; jev-1.14.0 is the preview (jev-preview). - Cloudflare Clef (Clef, Clef-flash, Clef-omni) — Cloudflare (Workers AI) · Decision model
Cloudflare-hosted decision models on Workers AI that take a state and a schema of typed questions (noul, choice, score) and return a probability for every allowed option. Three variants: Clef (27B), Clef-flash (9B), Clef-omni (30B MoE, 3B active). - Perplexity Decisions API (pplx-decider) — Perplexity · Decision model
Perplexity API endpoint that answers yes/no, multiple-choice, and scored questions about text and images with probabilities. - Inception Mercury Decide — Inception · Decision model
Decision model served at POST /v1/decisions (model mercury-decide) that evaluates named questions against a shared state and returns typed answers with probabilities. - Liquid AI d1 — Liquid AI · Decision model
Hosted decision model on the Liquid API (System One shape) returning noul, choice, and score answers with zero generated tokens; supports images. Open-weight variants also documented. - Strands Decider 2B (open source) — Strands Agents (AWS) · Open-weight decision model
Small open-source decision model (Qwen3.5-2B-Base + LoRA adapter + option-scoring head) for local routing, tool selection, guardrails, and evals. Apache-2.0, weights on Hugging Face. - AWS Bedrock Guardrails — AWS · Policy guardrail
Configurable guardrails: content filters, denied topics, PII handling, contextual grounding, and Automated Reasoning checks; returns block/allow plus assessments. - Content Safety in Foundry Control Plane (formerly Azure AI Content Safety) — Microsoft · Harm classifier
Microsoft harm classifiers with severity levels, Prompt Shields, and groundedness detection, now marketed as Content Safety in Foundry Control Plane. - Google Vertex AI / Gemini structured output — Google Cloud · Structured output
Constrain Gemini output to an enum or JSON schema and read logprobs; Model Armor for safety screening. Versioned model IDs. - Anthropic Claude (tool use / structured outputs) — Anthropic · Structured output
Use tool use / structured outputs to return JSON labels. No native probabilities. Available via Anthropic, Bedrock, and Vertex. - OpenAI Moderation (omni-moderation) — OpenAI · Harm classifier
Free harm classifier returning per-category scores for text and images. Only the continuously upgraded omni-moderation-latest alias is documented. - Cohere Classify — Cohere · Classifier
Few-shot / fine-tuned classification at POST /v1/classify returning per-label confidences. v1 path only; there is no v2 classify. - Laya (open source) — Convai Innovations · Open-weight decision model
Open-weight 421M encoder decision model (ModernBERT-large), Apache-2.0. laya-serve exposes a System One-style /v1/systemone endpoint; also runs in llama.cpp. - llama.cpp decision endpoint (/v1/systemone) — ggml-org (llama.cpp) · Open-weight decision model
llama-server in llama.cpp now serves a local System One-style /v1/systemone endpoint for open decision models. - Liquid AI d1-ultra — Liquid AI · Decision model
Larger hosted decision model from Liquid AI, listed on Liquid’s pricing page. No docs page found yet. - H2O-Lightning-4B (provisional) — H2O.ai · Open-weight decision model
Provisional listing: open-weight 4B decision model (Qwen3.5-4B), Apache-2.0, served via /v1/systemone. Facts come from search snippets only; the model card was not opened in full. - LLM Gateway — Decisions (provisional) — LLM Gateway · Gateway / proxy
Provisional listing: gateway with /v1/decisions (added Oct 12, 2026) and a deprecating /v1/systemone, serving Jev, GPT-6 Luna Decisions, and Microsoft-Decision-1. Facts from a changelog search snippet only.