> ## 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. # POST /v1/systemone: System One Typed Decisions > Ask a decision model typed questions (choice, score, yes/no) about an input and get probabilities back. Compatible with the System One API that TypeSafe Jev, vLLM Semantic Router and Ollama serve. The `/v1/systemone` endpoint takes the System One API's request and returns its response. A client written for TypeSafe's API or for a vLLM Semantic Router engine works against Rolter by changing its base URL and using a Rolter virtual key. Rolter authenticates the request, picks a target from the route, writes the target's upstream model into `model`, and forwards the body unchanged, so question types and fields Rolter has never seen still reach the model. Set up the decision servers behind it under [System One decisions](/configuration/system-one). ## Request **`POST /v1/systemone`** ### Headers `Bearer `: your Rolter virtual key. Must be `application/json`. ### Body The route name, for example `jev`. Rolter replaces it with the target's upstream model id (`jev-latest`, `vllm-sr/d3-edge`) before forwarding. Returns `404` if no route matches. The input the questions are about: a ticket, a message, a document, a JSON record. Questions keyed by ids you choose. Each answer comes back under the same id. Every question has a `type` and `instructions`; most have `criteria`: - `choice`: `criteria` maps each option to a description. The answer names the most likely option. - `score`: `criteria` is a list of 2 to 10 level descriptions, lowest first. The answer is a probability-weighted level. - `noul`: a yes/no question; `criteria` may describe `true` and `false`. The answer is the probability of yes. Other types (Vela's `span` and `set`, for example) are forwarded as written; whether they are answered depends on the model. Fields beyond these are forwarded as written too. Their names are upstream-specific. ### Images with OpenJev The Playground's **Decisions** mode accepts text or JSON state, a questions object, and one JPEG, PNG or WebP image. It sends the image separately as `image_data` (a base64 data URI), not as chat `messages`, `image_url`, or an `images` array: ```json { "model": "openjev", "state": "An image: <>", "image_data": "data:image/png;base64,", "questions": { "damaged": { "type": "noul", "instructions": "Is the parcel visibly damaged?" } } } ``` This follows [AlexWortega's OpenJev image-serving contract](https://huggingface.co/AlexWortega/openjev/blob/main/code/serving/IMAGE-SERVING.md), used by the image and frame-scoring examples in the [OpenJev Space](https://huggingface.co/spaces/AlexWortega/openjev). The image is shared by all questions; `<>` is optional and positions it in the premise. OpenJev appends it when absent. Limits are 4 MiB decoded and 12 million pixels. Remote image URLs and server file paths are not accepted. Vision needs a compatible upstream; `fake-llm` exercises the request shape but does not inspect pixels. The Space's video example samples frames and scores each separately; it is not a native video payload for this endpoint. The Playground renders choice probabilities, score legends, yes probabilities, confidence and per-question errors, with the full JSON response available below. Its model picker uses `rolter_capabilities` from the gateway model list, so a decision-only address is not offered in Chat. Older gateways without that metadata still offer `fake-llm` in Decisions; update the gateway to discover configured routes. ### Example ```bash curl https://gateway.example.com/v1/systemone \ -H "Authorization: Bearer $ROLTER_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "jev", "state": "Our checkout has returned 500 errors since 9am.", "questions": { "department": { "type": "choice", "instructions": "Which team owns this ticket?", "criteria": {"billing": "payments and refunds", "engineering": "software errors"} }, "is_urgent": {"type": "noul", "instructions": "Does this need action within the hour?"}, "impact": { "type": "score", "instructions": "How many customers are affected?", "criteria": ["one customer", "some customers", "every customer"] } } }' ``` ## Response The decision server's response, as it wrote it: ```json { "model": "jev-1.13.0", "answers": { "department": { "type": "choice", "choice": "engineering", "probabilities": { "billing": 0.03, "engineering": 0.97 }, "confidence": 0.91 }, "is_urgent": { "type": "noul", "noul": 0.96 }, "impact": { "type": "score", "score": 1.8, "legend": { "0": "one customer", "1": "some customers", "2": "every customer" }, "probabilities": { "0": 0.05, "1": 0.1, "2": 0.85 }, "confidence": 0.78 } }, "usage": { "input_tokens": 174, "output_tokens": 0 } } ``` `usage` drives the request's cost and its budget and rate-limit accounting. The response headers carry `x-rolter-provider` and `x-rolter-target`, as on every proxied endpoint. ## Errors | Status | Code | When | | ------ | ---------------------- | --------------------------------------------------------------------------------------------------- | | `400` | `unsupported_endpoint` | The route's targets cannot answer decisions (none is `system_one`, `openai_compatible` or `ollama`) | | `400` | `guardrail_blocked` | A guardrail rule matched text in `state` or in a question | | `401` | `invalid_api_key` | The virtual key is missing or not valid | | `404` | `model_not_found` | No route matches `model` | | `429` | | A rate limit or the route's caps refused the request | An error the decision server returns (TypeSafe's `422` for a malformed question, for example) reaches the caller unchanged. The reverse also holds: a route whose targets are all `system_one` refuses `/v1/chat/completions`, `/v1/messages`, `/v1/embeddings` and the audio endpoints with `400 unsupported_endpoint`, since a decision model cannot answer them. ## Without a decision server The built-in `fake-llm` model answers `choice`, `score` and `noul` questions deterministically and reports input-only usage, so the endpoint can be tried and tested with no key and no GPU: ```bash curl https://gateway.example.com/v1/systemone \ -H "Authorization: Bearer $ROLTER_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "fake-llm", "state": "hello", "questions": {"greeting": {"type": "noul", "instructions": "Is this a greeting?"}}}' ```