> ## Documentation index > Fetch the complete documentation index at: https://rolter-ai-rolter.docs7.io/llms.txt > Ask it with GET https://rolter-ai-rolter.docs7.io/ask?q=. Short keywords rank best. > Use these to discover all available pages before exploring further. # System One: Decision Models Through Rolter > Configure the system_one provider kind to put TypeSafe Jev, vLLM Semantic Router decision models or Ollama decision models behind Rolter's keys, budgets, rate limits and balancing. Decision models do not write text. They answer typed questions about an input (pick one of several options, score on a rubric, yes or no) and return probabilities and a confidence. They are used for routing, triage, classification and guard checks, where a generative model is slow and its answer has to be parsed. The servers below all speak one protocol, the System One API (`POST /v1/systemone`), and Rolter fronts all of them with one provider kind, `system_one`: | Server | Where it runs | `api_base` | | ------------------------------------------------------------------------------ | ---------------------------------------- | ------------------------- | | [TypeSafe Jev](https://docs.typesafe.ai/) | Hosted | `https://api.typesafe.ai` | | [vLLM Semantic Router](https://github.com/vllm-project/semantic-router) engine | Self-hosted (`vllm-sr serve -e `) | `http://vllm-sr:8899` | | [Ollama](https://docs.ollama.com/capabilities/decision) 0.35 or later | Self-hosted | `http://ollama:11434` | Callers send decisions to Rolter's [`POST /v1/systemone`](/api/system-one) with a Rolter virtual key. Virtual keys, budgets, rate limits, route caps, balancing, retries, request logs and cost all apply, as they do for chat. --- ## Configuration ```toml # TypeSafe's hosted Jev [[providers]] name = "typesafe" kind = "system_one" api_base = "https://api.typesafe.ai" api_key_env = "TYPESAFE_API_KEY" # a self-hosted vLLM Semantic Router engine serving vllm-sr/d3-edge [[providers]] name = "vllm-sr" kind = "system_one" api_base = "http://vllm-sr:8899" [[routes]] model = "jev" strategy = "round_robin" [[routes.targets]] provider = "typesafe" model = "jev-latest" ``` `api_base` is the server root, without `/v1`: Rolter appends `/v1/systemone` itself. The key, when the server takes one, is sent as `Authorization: Bearer`. An open vLLM Semantic Router listener and a local Ollama take no key, so leave it out for those. In the dashboard, pick **System One (decisions)** as the kind. The preview under **API base** shows the decision endpoint the provider will be called at. ### Health checks The free probe is `GET {api_base}/v1/models`, which TypeSafe and Ollama both answer with a model list. A vLLM Semantic Router engine publishes its list at `/v1/systemone/models` instead. If it answers `/v1/models` with a `404`, the provider still reads as healthy, since any answer below `500` does, but its models are not discovered, so name them on the route targets. The opt-in [LLM-call check](/reliability/health-checks#end-to-end-llm-call-checks) asks one yes/no question and proves a decision works end to end. --- ## Pricing Rolter ships no price list. Jev bills input tokens only, at $0.042 per million tokens as of October 2026 ([TypeSafe models](https://docs.typesafe.ai/models)); output is free. That is a price row with a zero output rate: ```toml [[model_prices]] model = "jev" input_per_mtok = 0.042 output_per_mtok = 0 ``` The cost of each decision is read from the `usage.input_tokens` and `usage.output_tokens` the server reports, so request logs never mark a decision as having unknown usage. A self-hosted server's tokens cost whatever you price them at, including nothing. --- ## Which endpoints a decision model answers A decision model cannot generate text, embed or transcribe, and a hosted chat API has no decision endpoint. Rolter checks this per route, before anything is forwarded: - A route whose targets are all `system_one` answers only `POST /v1/systemone`. A chat, embeddings or audio request for it gets `400` with code `unsupported_endpoint` and a message naming `/v1/systemone`. - `POST /v1/systemone` needs a route with at least one target of kind `system_one`, `openai_compatible` or `ollama`. The last two are allowed because a self-hosted server or another gateway behind them may serve the endpoint beside chat. A decision for any other route gets the same `400`. Keep decision models in routes of their own. A route that mixes decision and chat targets is not refused, and requests of either kind will reach targets that cannot answer them. It is reported, though: `rolter check`, the gateway at startup and the dashboard's config problems all name such a route and the targets on each side. --- ## Guardrails and privacy [Guardrails](/security/guardrails) scan every string in the decision's `state` and in each question's `instructions` and `criteria`, so a redaction rule masks an email inside a ticket the same way it does inside a chat message, and a block rule refuses the request. Question ids, option keys and `type` are never rewritten. Images and videos are not scanned. The external PII sanitizer and the guardrail webhook receive the whole request body, as they do for every endpoint. --- ## Limits Rolter does not cap the number of questions; the servers do (Ollama takes up to 64, Jev a 64k-token context per request). The request body is bounded by `server.max_body_bytes`. vLLM Semantic Router's d3 models accept images and video in the body, so a deployment sending video may need to raise that limit. Without a key or a GPU, use the built-in `fake-llm` model: it answers `choice`, `score` and `noul` questions deterministically.