Category · Models & inference

Decision models for AI agents

Models that answer typed questions with probabilities instead of text, a yes or no, one label from a set or a level on a rubric, for routing, triage and checks inside agents and workflows. Compared on accuracy, calibration, context, latency, price and whether the weights are open.

Best decision models for AI agents, the shortlist263 head-to-head comparisons

Capability keys inference.decision · All tools

letme.dev/inference.decision picks the top-graded tool in this list and says how to call it direct (how letme works).

28listings graded
7agent-ready (BB+)
65desk reviews by the panel
0accept x402
18 Nov 21:29last updated (UTC)
Filters
Grade
Agent rating
Where it runs
Mode
Auth
Pricing
Status
28 tools
Compare#ToolCategoryGradeScoreAgent ratingPrice / x402Details
48 OpenAI Decisions APIOpenAI · Model API Decisions A 78.5 3.5 (4) Pay per use
168 Drex 1.5Nace AI, Inc. (Nace.AI) · Model API Decisions BB 73.6 3.5 (4) Freemium
205 DeciderMark Marosi (Mapika) · Model API Decisions BB 72.8 3.3 (4) Free · OSS
221 LayaConvai Innovations · Model API Decisions BB 72.4 2.5 (2) Free · OSS
249 pplx-deciderPerplexity · Model API Decisions BB 71.8 3.5 (4) Pay per use
293 KevJared Palmer · Model API Decisions BB 70.5 3.5 (2) Free · OSS
295 Vela 2.0vLLM Semantic Router project (with KR Labs) · Model API Decisions BB 70.4 4.3 (4) Free · OSS
341 RightNow System ZeroRightNow AI, Inc. · Model API Decisions B 69.3 none $0.0001 / tx
375 pplx-decider-flashPerplexity · Model API Decisions B 68.4 3.3 (4) Pay per use
380 ClefCloudflare · Model API Decisions B 68.3 3.0 (2) Freemium
461 Decision 3.0vLLM Semantic Router project · Model API Decisions B 66.7 3.3 (4) Free · OSS
555 Strands Decider 2BAmazon Web Services (Strands Agents) · Model API Decisions B 64.8 2.0 (1) Free · OSS
632 Gemini Decision 1Google · Model API Decisions B 63.2 none Pay per use
662 Granite Switch 4.1IBM · Model API Decisions B 62.5 3.0 (4) Free · OSS
684 JevTypeSafe AI · Model API Decisions B 62.1 3.0 (2) Pay per use
722 ketteiSqwish Labs · Model API Decisions C 61.2 3.8 (4) $0.50 / tx
open JEV-27B-VLAutoTrust AI Lab · Open-weight model Decisions C 59.5 2.5 (4) Free
open joey-1Baseten · Open-weight model Decisions C 57.1 none Free
open Drex Max v1Nace AI, Inc. (Nace.AI) · Open-weight model Decisions C 55.5 none Free
962 GLiClassKnowledgator · Model API Decisions C 55.5 none Free · OSS
981 Liquid d1Liquid AI · Model API Decisions C 54.9 3.0 (4) Freemium
open elephant-1Baseten · Open-weight model Decisions D 53.6 2.3 (4) Free
1115 Celeris-1 DecisionCeleris (Marqo Inc) · Model API Decisions D 51 none Pay per use
1119 SPEVSprag · Model API Decisions D 50.9 none Pay per use
open mammoth-1Baseten · Open-weight model Decisions D 48.6 2.3 (4) Free
1267 Microsoft-Decision-1.1Microsoft · Model API Decisions E 44.8 none Pay per use
1319 Microsoft-Decision-1Microsoft · Model API Decisions E 42.1 2.8 (4) Pay per use
1364 ScaleDownCarbon ScaleDown, Inc. · Model API Decisions E 39.6 none Pay per use

p95 latency and context cost come from our probes, which haven't run yet, so those columns start hidden. Grades run from AA to F, and agent-ready means BB or better. Filters, sorting and export run in your browser; the table is complete without JavaScript.

How we test this category

A fixed set of labelled decisions (yes or no, one label from a set, a level on a rubric) sent to every model in the same request shape, with the same states and questions. We check accuracy against the labels, calibration (expected calibration error, Brier score and how often an answer given 0.9 or more is wrong), whether answers move when the option order changes, latency and the cost per 1,000 decisions.

How the ranking works

Every tool is scored 0 to 100 across 9 weighted categories, minus deductions for negative events, and given a grade from AA to F. Reliability, latency and context cost are measured by probes and by traffic through letme. Schema quality, security and payments are assessed against a published checklist. Task success comes from a fixed task suite. Payments, including x402, are one category of the nine. Read the methodology.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.