> ## Documentation Index > Fetch the complete documentation index at: https://docs.liquid.ai/llms.txt > Use this file to discover all available pages before exploring further. # Make decisions > Answer typed questions about a state with calibrated probabilities, using TypeSafe's System One API. See [Decisions](https://docs.liquid.ai/api/guides/decisions). ## OpenAPI ````yaml /api/openapi.json post /decisions/v1/systemone openapi: 3.1.0 info: title: Liquid inference API version: 1.0.0 description: >- OpenAI-compatible inference API plus native endpoints. **Authentication** — Every request needs an API key, sent as a bearer token: `Authorization: Bearer $LIQUID_API_KEY`. Create a key on the [API keys](https://console.liquid.ai/dashboard/api-keys) page of Liquid Console; it is shown once. **Batch uploads** — Batch input files are uploaded through a presigned URL from `POST /v1/files`; see the [Batch guide](https://docs.liquid.ai/api/guides/batch). **Decision models** — `POST /decisions/v1/systemone` implements TypeSafe's System One API for typed Choice, Score, and Noul decisions from decision models such as `d1.1` and `d1-ultra`. servers: - url: https://api.liquid.ai security: - apiKey: [] tags: - name: Models - name: Chat - name: Decision models - name: Files - name: Batches - name: Large uploads paths: /decisions/v1/systemone: post: tags: - Decision models summary: Make decisions description: >- Answer typed questions about a state with calibrated probabilities, using TypeSafe's System One API. See [Decisions](https://docs.liquid.ai/api/guides/decisions). operationId: decisions requestBody: required: true content: application/json: schema: type: object properties: model: type: string description: >- The decision model id to use. `d1:latest` and `d1-ultra:latest` always point to the newest model of their family; pin an exact id such as `d1-ultra` to keep the same model. example: $DECISION_MODEL_ID state: description: >- The content the questions are about: plain text, or structured JSON such as a chat log or record. Omit or send null when the questions stand alone. As in Perplexity's Decisions API, an array state may also hold images as OpenAI-style `{ "type": "image_url", "image_url": { "url": "data:…" } }` parts: they are taken out of the state and checked under the same rules as `images`, which the request must then leave out (sending both returns 422), and a single string left beside them becomes the text state. images: type: array items: {} description: >- Up to 8 images the questions are about, for decision models that accept images: those listing `image` in `input_modalities` from GET /decisions/v1/models, such as `d1`. Other models return 422. Each is a base64 `data:image/…;base64,` URL or a `{ "content_type", "base64" }` object: JPEG, PNG, or WebP, 5 MB each, within the 4.5 MB request body limit. Remote image URLs are not accepted. Images come before the state in the prompt, in the order sent, and every question sees all of them. On `d1` and `d1-ultra`, an image costs 1.5 input tokens per 32×32-pixel patch that covers it (`ceil(width / 32) × ceil(height / 32)` patches), rounded up per image, and a request is billed its images once, however many questions it asks. The images of a request may cover at most 10,000 patches in all, and no image may be more than 100 times as long as it is wide; either returns 422. This is an extension to the System One API; omit it to stay TypeSafe-compatible. questions: type: object additionalProperties: true description: >- Up to 128 named questions; answers come back under the same keys. Each has a `type` ("choice", "score", or "noul") and `instructions` (a string or JSON). A Choice takes `criteria` mapping 2–255 option names to a description or null; a Score takes `criteria` as an ordered list of 2–10 level descriptions; a Noul takes optional `criteria` of `{ "true": …, "false": … }`, used only when both are given and say more than a bare yes and no. A request is billed its state and images once plus each question's own tokens, so asking a state several questions in one request costs far less than asking them in separate requests. Every question still reads the whole state, so the input limits apply to the state, images, and one question together: `d1` and `d1.1` allow 65,536 tokens and `d1-ultra` 32,768, and all three 250 KB of text, and they return 422 over either. required: - model - questions example: model: $DECISION_MODEL_ID 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 is_urgent: type: noul instructions: Does this convey urgency? frustration: type: score instructions: How frustrated is the customer? criteria: - Calm - Frustrated - Very angry responses: '200': description: Successful response. content: application/json: example: model: $DECISION_MODEL_ID answers: department: type: choice choice: technical probabilities: billing: 0.31 technical: 0.67 sales: 0.02 confidence: 0.5 is_urgent: type: noul noul: 0.95 frustration: type: score score: 1.05 legend: '0': Calm '1': Frustrated '2': Very angry probabilities: '0': 0 '1': 0.95 '2': 0.05 confidence: 0.92 usage: input_tokens: 912 output_tokens: 0 schema: type: object properties: model: type: string description: The model that answered. answers: type: object additionalProperties: true description: >- One answer per question id. Choice: `choice`, `probabilities` per option, `confidence`. Score: `score` (probability-weighted, may fall between levels), `legend`, `probabilities` per level, `confidence`. Noul: `noul`, the probability of yes. Confidence runs from 0 (probability spread evenly) to 1 (all on one answer); for a Score it also counts how far the probability sits from the most likely level, so a split between the two ends of the scale is 0. usage: type: object additionalProperties: true description: >- Token counts: { input_tokens, output_tokens }, plus `cost` in USD when the model is priced. `input_tokens` counts the state and images once and each question's own tokens. Output is always 0. '429': description: >- The organization's request or token limit for the model was exceeded. headers: Retry-After: description: Integral seconds until the request can be retried. schema: type: integer minimum: 1 x-ratelimit-limit-requests: description: >- Maximum requests per minute (per second when only that limit is set), when a request limit applies. schema: type: integer minimum: 1 x-ratelimit-remaining-requests: description: Requests remaining in that window. schema: type: integer minimum: 0 x-ratelimit-reset-requests: description: >- Rounded-up duration until that window resets, such as 42s or 1m0s. schema: type: string pattern: ^([1-9][0-9]*h)?([0-9]+m)?[0-9]+s$ x-ratelimit-limit-tokens: description: >- Estimated tokens per minute (per second when only that limit is set), when a token limit applies. schema: type: integer minimum: 1 x-ratelimit-remaining-tokens: description: Estimated tokens remaining in that window. schema: type: integer minimum: 0 x-ratelimit-reset-tokens: description: >- Rounded-up duration until that window resets, such as 42s or 1m0s. schema: type: string pattern: ^([1-9][0-9]*h)?([0-9]+m)?[0-9]+s$ content: application/json: example: error: message: >- Rate limit exceeded for model `$MODEL_ID`. To request a higher limit, contact us at https://www.liquid.ai/connect. type: rate_limit_error param: null code: rate_limit_exceeded x-codeSamples: - lang: curl label: cURL source: |- curl https://api.liquid.ai/decisions/v1/systemone \ -H "Authorization: Bearer $LIQUID_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "$DECISION_MODEL_ID", "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" } }, "is_urgent": { "type": "noul", "instructions": "Does this convey urgency?" }, "frustration": { "type": "score", "instructions": "How frustrated is the customer?", "criteria": ["Calm", "Frustrated", "Very angry"] } } }' components: securitySchemes: apiKey: type: http scheme: bearer description: >- A Liquid API key from the [API keys](https://console.liquid.ai/dashboard/api-keys) page of Liquid Console, sent as `Authorization: Bearer $LIQUID_API_KEY`. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.