> ## Documentation Index > Fetch the complete documentation index at: https://docs.omniall.ai/llms.txt > Use this file to discover all available pages before exploring further. # TypeSafe System One > Official TypeSafe System One request. Send `state` (shared content) and a map of questions (`noul` / `choice` / `score`). Each question is answered independently against the same `state`. Context limit: 64k tokens total; `state` + the longest single question ≤ 32k (or 262k with `TypeSafe-Danger-Zone-Long-Context: true`). ## Question types | `type` | `criteria` | Answer fields | | - | - | - | | `noul` | optional `{ true, false }` | `noul` = P(yes) | | `choice` | required option map (≤ 255) | `choice`, `probabilities`, `confidence` | | `score` | required ordered array (2–10) | `score`, `legend`, `probabilities`, `confidence` | `state` and `instructions` may be string, object, or array. Keys in `questions` are echoed in `answers`. How-to: [TypeSafe Jev API](https://docs.omniall.ai/typesafe-jev-api.md). ## OpenAPI ````yaml openapi/typesafe-jev.yaml POST /typesafe/v1/systemone openapi: 3.1.0 info: title: Omniall AI — TypeSafe Jev (System One) version: 1.14.0 description: > TypeSafe Jev System One decision APIs on Omniall AI. Jev does **not** generate text. You send content (`state` / `input`) and typed questions; it returns answers with probabilities (and confidence where applicable). **Two call styles:** - TypeSafe official: `POST /typesafe/v1/systemone` - OpenAI Decisions: `POST /v1/decisions` **Models:** `jev-1.14.0`, `jev-preview` (alias of current preview), `jev-latest`. **Host:** `https://api.omniall.ai` · Auth `Authorization: Bearer sk-...` Preview headers (optional): - `TypeSafe-Danger-Zone-Images: true` — allow images in TypeSafe official requests - `TypeSafe-Danger-Zone-Long-Context: true` — raise context limit to 262k tokens servers: - url: https://api.omniall.ai security: [] tags: - name: TypeSafe System One description: TypeSafe official System One format - name: OpenAI Decisions description: OpenAI Decisions-compatible format paths: /typesafe/v1/systemone: post: tags: - TypeSafe System One summary: TypeSafe System One description: > Official TypeSafe System One request. Send `state` (shared content) and a map of questions (`noul` / `choice` / `score`). Each question is answered independently against the same `state`. Context limit: 64k tokens total; `state` + the longest single question ≤ 32k (or 262k with `TypeSafe-Danger-Zone-Long-Context: true`). operationId: typeSafeSystemOne parameters: - $ref: '#/components/parameters/Authorization' - name: TypeSafe-Danger-Zone-Images in: header required: false schema: type: string enum: - 'true' description: >- Preview — allow image assets in `state` / `instructions` / `criteria`. - name: TypeSafe-Danger-Zone-Long-Context in: header required: false schema: type: string enum: - 'true' description: >- Preview — raise context limits to 262k tokens (slower, lower accuracy). requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/TypeSafeSystemOneRequest' examples: ticket_routing: summary: Ticket routing (choice + score + noul) value: model: jev-1.14.0 state: Help! My payouts have been failing for 3 days. questions: department: type: choice instructions: Which team should handle this? criteria: billing: Payments, invoicing, refunds technical: Bugs, outages, integrations sales: Pricing, upgrades, new accounts frustration: type: score instructions: How frustrated is the customer? criteria: - Calm - Frustrated - Very angry is_urgent: type: noul instructions: Does this convey urgency? responses: '200': description: Answers for each question content: application/json: schema: $ref: '#/components/schemas/TypeSafeSystemOneResponse' examples: ticket_routing: value: model: jev-1.14.0 answers: department: type: choice choice: billing probabilities: billing: 0.88 technical: 0.12 sales: 0 confidence: 0.81 frustration: type: score score: 1.05 legend: '0': Calm '1': Frustrated '2': Very angry probabilities: '0': 0 '1': 0.95 '2': 0.05 confidence: 0.92 is_urgent: type: noul noul: 0.95 usage: input_tokens: 318 output_tokens: 34 '400': $ref: '#/components/responses/TypeSafeError' '401': $ref: '#/components/responses/TypeSafeError' '403': $ref: '#/components/responses/TypeSafeError' '429': $ref: '#/components/responses/TypeSafeError' components: parameters: Authorization: name: Authorization in: header required: true schema: type: string example: Bearer sk-... description: Bearer API key, e.g. `Bearer sk-...`. schemas: TypeSafeSystemOneRequest: type: object required: - model - state - questions properties: model: type: string description: Model id. Use `jev-1.14.0`, or aliases `jev-preview` / `jev-latest`. example: jev-1.14.0 state: description: Shared content to judge (string, object, or array). oneOf: - type: string - type: object additionalProperties: true - type: array items: {} example: Help! My payouts have been failing for 3 days. questions: type: object description: Map of question id → question. Keys are echoed in `answers`. additionalProperties: $ref: '#/components/schemas/TypeSafeQuestion' minProperties: 1 assets: type: object description: > Preview — image assets keyed by UUID/reference string used inside `state` / `instructions` / `criteria`. Requires header `TypeSafe-Danger-Zone-Images: true`. additionalProperties: $ref: '#/components/schemas/TypeSafeAsset' TypeSafeSystemOneResponse: type: object properties: model: type: string example: jev-1.14.0 answers: type: object additionalProperties: oneOf: - $ref: '#/components/schemas/TypeSafeNoulAnswer' - $ref: '#/components/schemas/TypeSafeChoiceAnswer' - $ref: '#/components/schemas/TypeSafeScoreAnswer' usage: type: object properties: input_tokens: type: integer output_tokens: type: integer TypeSafeQuestion: type: object required: - type - instructions properties: type: type: string enum: - noul - choice - score description: | - `noul` — yes/no, returns P(yes) - `choice` — pick one option (≤ 255) - `score` — score on 2–10 ordered levels instructions: description: Question text (string, object, or array). oneOf: - type: string - type: object additionalProperties: true - type: array items: {} criteria: description: > Required for `choice` (option map) and `score` (ordered level array). Optional for `noul` as `{ "true": "...", "false": "..." }`. oneOf: - type: object additionalProperties: true - type: array items: {} TypeSafeAsset: type: object required: - type - data_base64 properties: type: type: string enum: - image format: type: string enum: - png - jpg description: Image format. Dimensions 256–1568 px per side, ≤ 16 MiB. data_base64: type: string description: Raw base64 without `data:` prefix. TypeSafeNoulAnswer: type: object properties: type: type: string enum: - noul noul: type: number minimum: 0 maximum: 1 description: Probability that the answer is yes. TypeSafeChoiceAnswer: type: object properties: type: type: string enum: - choice choice: type: string description: Highest-probability option. probabilities: type: object additionalProperties: type: number confidence: type: number minimum: 0 maximum: 1 description: >- How peaked the distribution is (not the same as the top option probability). TypeSafeScoreAnswer: type: object properties: type: type: string enum: - score score: type: number description: Probability-weighted score (may fall between levels). legend: type: object additionalProperties: type: string probabilities: type: object additionalProperties: type: number confidence: type: number minimum: 0 maximum: 1 responses: TypeSafeError: description: TypeSafe-style error content: application/json: schema: type: object properties: detail: type: object properties: error_type: type: string example: validation_error message: type: string example: >- questions.refund.type: expected one of 'noul', 'choice', 'score' ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.