> ## Documentation Index > Fetch the complete documentation index at: https://docs.sqwish.ai/llms.txt > Use this file to discover all available pages before exploring further. # Estimate billable input and maximum cost without executing > Counts customer input using the pinned billing tokenizer and resolves the current model and fallback price. Reserves no credit and runs no model. Estimates consume their own account token budget; the execution policy and available balance are checked again when the request is submitted. ## OpenAPI ````yaml /openapi.json post /v1/decide/estimate openapi: 3.1.0 info: title: DecisionOne workbench description: >- Native decisions, immutable datasets, adaptation and shared-base deployment. Authenticate with `Authorization: Bearer d1_sk_...` when accounts are on. A short guide for coding agents is at /llms.txt. Hosted account APIs accept a Bearer API key or a browser session. Browser mutations require the configured Origin and X-CSRF-Token from /auth/session. Account recovery and history remain available to blocked accounts. Waitlisted accounts can read their account summary and model catalogue and request early access; private member APIs require admission. Money fields ending in _usd are exact decimal strings; never interpret them as integer cents. Authenticated customer reads and existing-operation replays share read_rpm. Exhausted budgets return 429 with Retry-After; unavailable admission storage returns 503. version: 0.1.0 servers: - url: https://console.sqwish.ai security: [] tags: - name: Decisions description: Probabilities for questions with fixed outcomes. - name: Feedback description: Report outcomes and turn them into training data. - name: Models description: Base models, adapters and named models with versions. - name: Datasets description: Validated training examples. A dataset never changes. - name: Fine-tuning description: Training jobs, their events and held-out results. - name: Prompt tuning description: Better wording for a decision, tested on your rows. Words, not weights. - name: Labeling description: Teacher labels for real queries, reviewed by you. - name: Accounts description: Email OTP sign-in, revocable sessions, security and API keys. - name: Billing description: Exact USD balances, purchases, automatic top-ups and referrals. - name: Integrations description: Endpoints other tools call, such as Claude Code. - name: System description: Health and discovery. paths: /v1/decide/estimate: post: tags: - Decisions summary: Estimate billable input and maximum cost without executing description: >- Counts customer input using the pinned billing tokenizer and resolves the current model and fallback price. Reserves no credit and runs no model. Estimates consume their own account token budget; the execution policy and available balance are checked again when the request is submitted. operationId: estimateDecisions requestBody: content: application/json: schema: $ref: '#/components/schemas/DecideRequest' required: true responses: '200': description: Successful Response content: application/json: schema: properties: currency: type: string const: USD title: Currency input_tokens: type: integer title: Input Tokens tokenizer: $ref: '#/components/schemas/Tokenizer' maximum_charge_usd: title: Maximum Charge Usd type: string models: items: $ref: '#/components/schemas/ModelQuote' title: Models type: array required: - currency - input_tokens - tokenizer - maximum_charge_usd - models title: Estimate type: object 4XX: description: >- Client error. On a 422, `error.details` lists each field that failed. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' 5XX: description: Server error. A 503 names what is not running on this server. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - BearerAuth: [] components: schemas: DecideRequest: properties: model: anyOf: - type: string maxLength: 128 minLength: 1 - type: 'null' title: Model context: anyOf: - type: string - additionalProperties: true type: object - items: {} type: array title: Context decisions: items: $ref: '#/components/schemas/Decision' type: array maxItems: 64 minItems: 1 title: Decisions independent: type: boolean title: Independent default: false store: anyOf: - type: boolean - type: 'null' title: Store metadata: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Metadata fallback: anyOf: - type: string enum: - auto - none - items: type: string type: array - type: 'null' title: Fallback additionalProperties: false type: object required: - context - decisions title: DecideRequest Tokenizer: properties: name: type: string title: Name revision: type: string title: Revision type: object required: - name - revision title: Tokenizer ModelQuote: properties: id: type: string title: Id quote_usd: type: string title: Quote Usd type: object required: - id - quote_usd title: ModelQuote ErrorResponse: description: >- The body of every error. app.failure() builds it; this model documents it. properties: error: $ref: '#/components/schemas/ErrorBody' required: - error title: ErrorResponse type: object Decision: properties: id: type: string maxLength: 128 minLength: 1 title: Id question: anyOf: - type: string - additionalProperties: true type: object - items: {} type: array title: Question kind: type: string enum: - single - binary - ordinal title: Kind default: single outcomes: title: Outcomes rubric: anyOf: - items: {} type: array - type: 'null' title: Rubric weights: anyOf: - additionalProperties: type: number type: object - type: 'null' title: Weights costs: anyOf: - additionalProperties: additionalProperties: type: number type: object type: object - type: 'null' title: Costs abstain: anyOf: - $ref: '#/components/schemas/Abstain' - type: 'null' additionalProperties: false type: object required: - id - question title: Decision ErrorBody: properties: code: description: A stable code to branch on, such as invalid_request. title: Code type: string message: description: What went wrong and what to change, in plain words. title: Message type: string retryable: description: >- True when another attempt may succeed; it does not prove that no work was done. Respect Retry-After when present. Only operations that support Idempotency-Key replay a prior result, including /v1/decide for 24 hours. title: Retryable type: boolean request_id: description: Also sent as X-Request-ID. Quote it in bug reports. title: Request Id type: string details: anyOf: - items: $ref: '#/components/schemas/ErrorDetail' type: array - type: 'null' default: null description: On validation errors, one entry for each field that failed. title: Details required: - code - message - retryable - request_id title: ErrorBody type: object Abstain: properties: min_probability: anyOf: - type: number maximum: 1 minimum: 0 - type: 'null' title: Min Probability cost: anyOf: - type: number - type: 'null' title: Cost additionalProperties: false type: object title: Abstain ErrorDetail: properties: path: description: Where the problem is, such as ["body", "decisions", 0, "outcomes"]. items: anyOf: - type: string - type: integer title: Path type: array message: title: Message type: string type: anyOf: - type: string - type: 'null' default: null title: Type required: - path - message title: ErrorDetail type: object securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: d1_sk_... description: Create an API key in the console. Required when accounts are enabled. ````