Free to start

Decision Models s1-pro-2 (GLOBAL)

Try Decision Models s1-pro-2 (GLOBAL) on us. Starter credit covers your first requests, then one key reaches this route and every other model in the catalog.

`decisionmodelsio/s1-pro-2`

decisionmodelsio

All models

Publisher	decisionmodelsio
AI IQ	No AI IQ profile matched yet.
Context	8,192 tokens
Providers	Decision Models (Global)
Credits routes	1 provider route
Modes	decide
Billing	Credits

How to use Decision Models s1-pro-2 (GLOBAL)

Current Pro version: a 27B open typed-decision model served in NVFP4; noul/choice/score answers with probabilities. Text only; up to 3 questions per request, each answered separately, with at most 8,192 input tokens per question including the state. Billed at the s1-pro price.

Input	POST /v1/decide: state (at most 16 KiB serialized JSON) and exactly one boolean/noul, choice or score question. The model's input-token limit also applies. No streaming.
Output	Verified answers and probabilities, with inputTokens usage. Input-only billing; output tokens are free. The EU route cannot fall back to Global.

Example input

{"model": "decisionmodelsio/s1-pro-2", "state": "Mia owns a red bicycle.", "questions": {"color": {"type": "choice", "instructions": "Which color is the bicycle?", "criteria": {"red": null, "blue": null}}}}

Example output

{"model": "decisionmodelsio/s1-pro-2", "answers": {"color": {"type": "choice", "choice": "red", "probabilities": {"red": 0.99, "blue": 0.01}}}}

Current route evidence

Live leaderboard

$0.04009/1MLowest Credits input price

selected routeLowest Credits output price

not enough dataFastest measured p50 TTFT

not enough dataHighest measured throughput

Recent provider-route uptime spans not enough data across 1 route and 1 provider. Price comes from the current Credits catalog. Speed and uptime come from routed probes rather than vendor claims.

Providers serving this model

Sorted by lowest combined prompt and completion price. Use "provider": {"sort": "throughput"} in the request body (or append :nitro to the model id) to route to the fastest provider instead.

Trust boundary: TR router attestation verifies the TrustedRouter gateway only. Provider policy separately describes the upstream model host's retention, confidential compute, and E2EE posture. Company country is separate from inference location. Weight formats are source-backed declarations, not per-request proofs.

Provider	Input	Cached input	Output	Weight format	Provider policy	Company / inference location	Measured speed
Decision Models (Global)decisionmodelsio	$0.04009/1M	Not published	selected route	Unknown	privacy unknown Retention details Typed decision models, not chat completions. Decision Models states that prompts and outputs are processed in memory, never stored or used for training. Operational billing metadata is retained. No confidential-compute or E2EE claim is made. Global uses spare EU capacity and may use worldwide capacity for opted-in keys; it is not an EU residency guarantee. Provider policy source	Operator country: DE Location details Headquarters / registered office: Not verified. Inference: Global, dynamically scheduled inference; no fixed-country residency commitment. Global uses spare EU capacity, with worldwide Lium capacity available to opted-in keys; the complete country set is not published. Region pinning through TR: Use decisionmodelsio/s1-fast, s1-pro or s1-vision. The gateway pins S1-Region=global and a separate regional key; no cross-tier fallback. Reviewed 2026-10-09. Regional processing and pricing Processing locations API contract Full location evidence	TTFT: insufficient data Speed: insufficient data

Speed is the median (p50) from TR's recent measured requests for this exact model and provider, refreshed from the cached leaderboard. At least two timing samples are required; workload and network conditions affect results. Performance details

Compare Decision Models s1-pro-2 (GLOBAL)

All comparisons

Decision Models s1-pro-2 (GLOBAL) vs Z.ai: GLM 5.334 combined provider routes

Questions

What model ID should I use for Decision Models s1-pro-2 (GLOBAL)?

Use decisionmodelsio/s1-pro-2 as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.

Which providers serve Decision Models s1-pro-2 (GLOBAL)?

TrustedRouter currently lists Decision Models (Global) for Decision Models s1-pro-2 (GLOBAL). Provider availability and routing eligibility can change as catalog and health data update.

How much does Decision Models s1-pro-2 (GLOBAL) cost through TrustedRouter?

The current lowest Credits input price is $0.04009/1M and the lowest Credits output price is selected route. Prices are per one million tokens and come from the current route catalog.

How do I require zero data retention for Decision Models s1-pro-2 (GLOBAL)?

Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.