> ## Documentation Index > Fetch the complete documentation index at: https://docs.budgetpixel.com/llms.txt > Use this file to discover all available pages before exploring further. # Estimate the cost of a request > Returns the credit cost of a generation request **without running it**. Send the same body you'd send to the generate endpoint, plus `model`. The cost is computed by the same logic that bills you, so it can't disagree with the invoice. `exact` is `true` for deterministic pricing. For seedream's sequential mode (the model chooses how many images, up to `max_images`) `credits` is the ceiling we reserve and `exact` is `false` — the real charge is always ≤ it. Failed jobs cost nothing, so you're never charged more than `credits`. ## OpenAPI ````yaml /openapi.yaml post /cost openapi: 3.1.0 info: contact: email: support@budgetpixel.com name: BudgetPixel Support description: > The BudgetPixel developer API for programmatic image and video generation. Generation is **asynchronous**: you create a job, then poll its status until it reaches a terminal state (`succeeded` / `failed`). You are charged in credits only on success — never for failures, timeouts, or content blocked before generation. **Authentication.** All requests require an API key sent as a bearer token: Authorization: Bearer bpx_live_xxx Create and manage keys from your BudgetPixel account dashboard. The developer API is currently available on the **Ultra** plan. **Pricing.** API usage is metered in credits at each model's published price (see `GET /v1/models`). Consumer subscription perks (free daily generations, free-for-Ultra models, subscription discounts) do not apply to API traffic. title: BudgetPixel API version: '2026-06-20' servers: - description: Production url: https://api.budgetpixel.com/v1 security: - ApiKeyAuth: [] tags: - description: Account and credit balance name: Account - description: Discover available models and pricing name: Models - description: Upload input media for image/video generation name: Uploads - description: Image job status name: Images - description: FLUX image models name: Black Forest Labs - description: SeeDream image models name: Bytedance - description: Video job status name: Videos - description: Kuaishou Kling video models name: Kling - description: SeeDance video models name: ByteDance (SeeDance) - description: Music job status name: Audios - description: Music generation models name: Music - description: Format conversion for images, video, and audio name: Conversions - description: Publish posts to your BudgetPixel feed name: Social - description: Content moderation — NSFW rating and CSAM detection name: Moderation - description: Content classification — music genre detection name: Classification paths: /cost: post: tags: - Models summary: Estimate the cost of a request description: > Returns the credit cost of a generation request **without running it**. Send the same body you'd send to the generate endpoint, plus `model`. The cost is computed by the same logic that bills you, so it can't disagree with the invoice. `exact` is `true` for deterministic pricing. For seedream's sequential mode (the model chooses how many images, up to `max_images`) `credits` is the ceiling we reserve and `exact` is `false` — the real charge is always ≤ it. Failed jobs cost nothing, so you're never charged more than `credits`. operationId: estimateCost requestBody: content: application/json: example: length_seconds: 5 model: seedance-2.0 resolution: 1080p schema: additionalProperties: true properties: model: description: The model slug (image or video), e.g. `seedance-2.0`. type: string required: - model type: object required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/CostEstimate' description: The estimated cost. '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '403': $ref: '#/components/responses/Forbidden' '404': $ref: '#/components/responses/NotFound' '429': $ref: '#/components/responses/TooManyRequests' components: schemas: CostEstimate: description: >- The credit cost of a request. The real charge is always ≤ `credits` (failures cost nothing; sequential image jobs may use fewer images). properties: credits: description: >- Credits the request will cost — the maximum, for non-deterministic cases. example: 2750 type: integer exact: description: >- True when the cost is exact; false when `credits` is an upper bound (e.g. seedream sequential, where the model picks the image count). type: boolean model: example: seedance-2.0 type: string type: enum: - image - video type: string required: - model - type - credits - exact type: object Error: properties: error: properties: code: description: Stable machine-readable code. example: model_not_available type: string message: type: string type: description: Error category. example: invalid_request_error type: string required: - type - code - message type: object required: - error type: object responses: BadRequest: content: application/json: schema: $ref: '#/components/schemas/Error' description: The request was malformed or referenced an unavailable model. Unauthorized: content: application/json: schema: $ref: '#/components/schemas/Error' description: Missing or invalid API key. Forbidden: content: application/json: schema: $ref: '#/components/schemas/Error' description: Authenticated but not permitted (plan gate, ownership, restriction). NotFound: content: application/json: schema: $ref: '#/components/schemas/Error' description: The requested job was not found. TooManyRequests: content: application/json: schema: $ref: '#/components/schemas/Error' description: Rate or queue limit reached. Retry after a short delay. securitySchemes: ApiKeyAuth: bearerFormat: bpx_live_* description: 'API key as a bearer token: Authorization: Bearer bpx_live_xxx' scheme: bearer type: http ````