> ## Documentation Index > Fetch the complete documentation index at: https://docs.voyager.so/llms.txt > Use this file to discover all available pages before exploring further. # Estimate Render > Roughly how long and how much a Vork render takes. With `from_job` or `sample` it scales this scene's own measured speed (scenes vary a lot); otherwise it uses recent real renders on that GPU, or built-in typical speeds until there are enough. `alternatives` gives the same job on the other Vork presets your plan runs, and `recommendation` names one that saves real wall time (a long render on render-2x or render-4x). ## OpenAPI ````yaml /openapi/voyager-api.yaml post /machines/estimate openapi: 3.1.0 info: title: Voyager API description: >- Generate images, video, speech, music, sound effects and 3D with your Voyager workspace's credits. Authenticate with `Authorization: Bearer vy_live_…`. Every response carries `X-Request-ID` and the `X-RateLimit-Limit` / `X-RateLimit-Remaining` / `X-RateLimit-Reset` (seconds until the window resets) headers; a 429 adds `Retry-After`. Errors share one envelope (`ErrorResponse`); a method a path does not take is 405 `method_not_allowed`. Some catalog operations run only through the Voyager MCP today (voice-change, text-to-motion, retexture, convert-3d, uv-unwrap; `x-voyager-mcp-only-operations`): this API's model listings leave them out. version: 1.0.0 x-voyager-agent-prompt: > Set up the Voyager API in this project. Voyager generates images, video, speech, music, sound effects, 3D, object masks, upscaled media and separated audio with the same models and credits as the Voyager app. Docs: https://docs.voyager.so/api (agent-readable: https://docs.voyager.so/llms.txt, OpenAPI: https://api.voyager.so/v1/openapi.json) 1. Key: read it from the env var VOYAGER_API_KEY. Never hard-code it or commit it; add VOYAGER_API_KEY= to .env.example and make sure .env is git-ignored. If it's missing, ask me to create one at https://voyager.so/dashboard/api (paid plans). 2. Base URL https://api.voyager.so/v1, header: Authorization: Bearer $VOYAGER_API_KEY 3. Pick a model: GET /models?type=image|video|speech|music|sound_effect|3d|segment|upscale|audio_separation. Read GET /models/{id} for its input_schema before building a request. 4. Optional cost check: POST /estimate with the same body as step 5; it returns estimated_charge (credits) and can_run. 5. Create: POST /jobs {"model": "", "operation": "", "input": {...}} with an Idempotency-Key header (a new UUID per logical request; reuse it when retrying the same request). 6. Wait: GET /jobs/{id}?wait=25 until status is succeeded, failed or canceled (honor Retry-After / poll_after_ms). Or pass "webhook_url" and verify the Standard Webhooks signature with the secret from the dashboard. 7. Results: job.outputs[].url is a signed link valid for 1 hour; download it right away, or GET /jobs/{id} again for a fresh link. Files are kept 30 days. 8. Errors are {"error": {"code","message","retryable",...}}. 402 = out of credits or not on a paid plan (show error.details.upgrade_url to me). 429 = slow down: wait Retry-After seconds. Retry only when retryable is true, with the same Idempotency-Key. Minimal example (curl): curl -s https://api.voyager.so/v1/jobs \ -H "Authorization: Bearer $VOYAGER_API_KEY" -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{"model":"nano-banana-2.1","operation":"text-to-image","input":{"prompt":"a red fox in snow","aspect_ratio":"16:9"}}' curl -s "https://api.voyager.so/v1/jobs/?wait=25" -H "Authorization: Bearer $VOYAGER_API_KEY" Write a small typed client (create → wait → download) with retries as above, then generate one test image to prove it works and tell me what it cost (job.credits.charged; if credits.state is still "pending", report job.credits.estimated and say it's an estimate). servers: - url: https://api.voyager.so/v1 description: Production security: [] paths: /machines/estimate: post: tags: - machines summary: Estimate Render description: >- Roughly how long and how much a Vork render takes. With `from_job` or `sample` it scales this scene's own measured speed (scenes vary a lot); otherwise it uses recent real renders on that GPU, or built-in typical speeds until there are enough. `alternatives` gives the same job on the other Vork presets your plan runs, and `recommendation` names one that saves real wall time (a long render on render-2x or render-4x). operationId: estimateCloudMachineRender requestBody: content: application/json: schema: $ref: '#/components/schemas/MachineEstimateRequest' required: true responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/MachineEstimate' headers: X-Request-ID: $ref: '#/components/headers/X-Request-ID' X-RateLimit-Limit: $ref: '#/components/headers/X-RateLimit-Limit' X-RateLimit-Remaining: $ref: '#/components/headers/X-RateLimit-Remaining' X-RateLimit-Reset: $ref: '#/components/headers/X-RateLimit-Reset' '400': description: The request is invalid (`INVALID_REQUEST`). content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: X-Request-ID: $ref: '#/components/headers/X-Request-ID' X-RateLimit-Limit: $ref: '#/components/headers/X-RateLimit-Limit' X-RateLimit-Remaining: $ref: '#/components/headers/X-RateLimit-Remaining' X-RateLimit-Reset: $ref: '#/components/headers/X-RateLimit-Reset' '401': description: Missing or invalid credential. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: X-Request-ID: $ref: '#/components/headers/X-Request-ID' X-RateLimit-Limit: $ref: '#/components/headers/X-RateLimit-Limit' X-RateLimit-Remaining: $ref: '#/components/headers/X-RateLimit-Remaining' X-RateLimit-Reset: $ref: '#/components/headers/X-RateLimit-Reset' '402': description: >- Not enough credits (`INSUFFICIENT_CREDITS`); `details.upgrade_url` links to billing. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: X-Request-ID: $ref: '#/components/headers/X-Request-ID' X-RateLimit-Limit: $ref: '#/components/headers/X-RateLimit-Limit' X-RateLimit-Remaining: $ref: '#/components/headers/X-RateLimit-Remaining' X-RateLimit-Reset: $ref: '#/components/headers/X-RateLimit-Reset' '403': description: >- This workspace needs a paid Voyager plan with a completed payment (`PLAN_REQUIRED`, `VERIFICATION_REQUIRED`; `details.upgrade_url`), or the key lacks a scope. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: X-Request-ID: $ref: '#/components/headers/X-Request-ID' X-RateLimit-Limit: $ref: '#/components/headers/X-RateLimit-Limit' X-RateLimit-Remaining: $ref: '#/components/headers/X-RateLimit-Remaining' X-RateLimit-Reset: $ref: '#/components/headers/X-RateLimit-Reset' '404': description: No such machine, job or path. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: X-Request-ID: $ref: '#/components/headers/X-Request-ID' X-RateLimit-Limit: $ref: '#/components/headers/X-RateLimit-Limit' X-RateLimit-Remaining: $ref: '#/components/headers/X-RateLimit-Remaining' X-RateLimit-Reset: $ref: '#/components/headers/X-RateLimit-Reset' '409': description: >- The machine is in the wrong state for this (e.g. `MACHINE_PAUSED`: resume it first, `MACHINE_NOT_READY`, `MACHINE_RELEASED`), or the Idempotency-Key was used for a different request. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: X-Request-ID: $ref: '#/components/headers/X-Request-ID' X-RateLimit-Limit: $ref: '#/components/headers/X-RateLimit-Limit' X-RateLimit-Remaining: $ref: '#/components/headers/X-RateLimit-Remaining' X-RateLimit-Reset: $ref: '#/components/headers/X-RateLimit-Reset' '429': description: Rate limited; retry after `Retry-After` seconds. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: X-Request-ID: $ref: '#/components/headers/X-Request-ID' X-RateLimit-Limit: $ref: '#/components/headers/X-RateLimit-Limit' X-RateLimit-Remaining: $ref: '#/components/headers/X-RateLimit-Remaining' X-RateLimit-Reset: $ref: '#/components/headers/X-RateLimit-Reset' Retry-After: $ref: '#/components/headers/Retry-After' '500': description: >- Something went wrong on our side. Retry, or quote request_id to support. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: X-Request-ID: $ref: '#/components/headers/X-Request-ID' X-RateLimit-Limit: $ref: '#/components/headers/X-RateLimit-Limit' X-RateLimit-Remaining: $ref: '#/components/headers/X-RateLimit-Remaining' X-RateLimit-Reset: $ref: '#/components/headers/X-RateLimit-Reset' '503': description: >- No capacity or a temporary outage; retry after `Retry-After` seconds. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' headers: X-Request-ID: $ref: '#/components/headers/X-Request-ID' X-RateLimit-Limit: $ref: '#/components/headers/X-RateLimit-Limit' X-RateLimit-Remaining: $ref: '#/components/headers/X-RateLimit-Remaining' X-RateLimit-Reset: $ref: '#/components/headers/X-RateLimit-Reset' security: - API Key: [] components: schemas: MachineEstimateRequest: properties: preset: anyOf: - type: string - type: 'null' title: Preset description: The preset to estimate for (`render`, the default). gpu: anyOf: - type: string - type: 'null' title: Gpu description: Or a GPU model, e.g. `L4`. frames: anyOf: - type: integer maximum: 10000000 minimum: 1 - type: 'null' title: Frames description: Frames to render (1 for a still). Or `seconds` and `fps`. seconds: anyOf: - type: number exclusiveMinimum: 0 - type: 'null' title: Seconds description: Video length in seconds (with `fps`). fps: anyOf: - type: number maximum: 1000 exclusiveMinimum: 0 - type: 'null' title: Fps description: Frames per second (with `seconds`). resolution: anyOf: - type: string - type: 'null' title: Resolution description: >- `720p`, `1080p`, `1440p`, `4k` (or `480p`, `WxH`). Default 1920x1080. width: anyOf: - type: integer maximum: 16384 minimum: 16 - type: 'null' title: Width description: Or a width in pixels (with `height`). height: anyOf: - type: integer maximum: 16384 minimum: 16 - type: 'null' title: Height description: Or a height in pixels (with `width`). profile: type: string enum: - std/previs - std/draft - std/final - std/path title: Profile description: The Vork render profile. default: std/final include_setup: anyOf: - type: boolean - type: 'null' title: Include Setup description: >- Add the one-time `vork setup` of a new machine. Default: true, unless the machine (`machine_id`, or `from_job`'s) already ran `vork setup`. machine_id: anyOf: - type: string - type: 'null' title: Machine Id description: 'A machine of yours: its GPU and image.' from_job: anyOf: - type: string - type: 'null' title: From Job description: >- A finished `vork render` job of this scene on one of your machines: scale its measured speed (basis `this_scene`). Its machine's GPU is used unless you name one. sample: anyOf: - $ref: '#/components/schemas/MachineRenderSample' - type: 'null' description: Or a render of this scene you timed yourself (basis `this_scene`). additionalProperties: false type: object title: MachineEstimateRequest MachineEstimate: properties: gpu: type: string title: Gpu description: The GPU the estimate is for. preset: anyOf: - type: string - type: 'null' title: Preset description: Its preset, when it matches one. frames: type: integer title: Frames description: Frames estimated. width: type: integer title: Width description: Width in pixels. height: type: integer title: Height description: Height in pixels. profile: type: string title: Profile description: The Vork render profile. seconds_low: type: number title: Seconds Low description: Fast end of the whole job, setup included when asked. seconds_typical: type: number title: Seconds Typical description: Typical whole job, setup included when asked. seconds_high: type: number title: Seconds High description: >- Slow end, including up to a couple of minutes of first-use scene compilation. seconds_per_frame: type: number title: Seconds Per Frame description: Typical seconds per frame at this size and profile. setup_seconds: type: number title: Setup Seconds description: Typical one-time `vork setup` seconds included (0 when not). usd_per_minute: anyOf: - type: number - type: 'null' title: Usd Per Minute description: The GPU's live price per minute (null when not offered now). credits_per_minute: anyOf: - type: number - type: 'null' title: Credits Per Minute description: The same in credits. usd_low: anyOf: - type: number - type: 'null' title: Usd Low description: Cost at `seconds_low`. usd_high: anyOf: - type: number - type: 'null' title: Usd High description: Cost at `seconds_high`. credits_low: anyOf: - type: number - type: 'null' title: Credits Low description: Credits at `seconds_low`. credits_high: anyOf: - type: number - type: 'null' title: Credits High description: Credits at `seconds_high`. basis: type: string enum: - default - measured - this_scene title: Basis description: >- `this_scene`: scaled from a render of this scene (`from_job` or `sample`); `measured`: from recent real Vork renders on this GPU; `default`: built-in typical speeds. samples: type: integer title: Samples description: Renders the estimate is based on (0 for `default`). note: type: string title: Note description: What to tell the user, for agents. alternatives: items: $ref: '#/components/schemas/MachineEstimateAlternative' type: array title: Alternatives description: >- The same job on the other Vork presets your plan runs (render-lite, render, render-2x, render-4x), frames split across a multi-GPU machine's GPUs. recommendation: anyOf: - $ref: '#/components/schemas/MachineEstimateRecommendation' - type: 'null' description: >- A preset that saves at least 30% of the wall time (and at least a minute) for at most 1.5x the total cost, the extra cost in its reason (null when none does). type: object required: - gpu - preset - frames - width - height - profile - seconds_low - seconds_typical - seconds_high - seconds_per_frame - setup_seconds - usd_per_minute - credits_per_minute - usd_low - usd_high - credits_low - credits_high - basis - samples - note title: MachineEstimate ErrorResponse: properties: error: $ref: '#/components/schemas/ErrorBody' description: What went wrong. type: object required: - error title: ErrorResponse description: Every non-2xx answer. MachineRenderSample: properties: frames: type: integer minimum: 1 title: Frames description: Frames the measured render made. seconds: type: number exclusiveMinimum: 0 title: Seconds description: How long it took (Vork's `Rendered N frames in X s`). width: type: integer maximum: 16384 minimum: 16 title: Width description: Its width in pixels. height: type: integer maximum: 16384 minimum: 16 title: Height description: Its height in pixels. profile: type: string enum: - std/previs - std/draft - std/final - std/path title: Profile description: Its Vork profile. default: std/final additionalProperties: false type: object required: - frames - seconds - width - height title: MachineRenderSample MachineEstimateAlternative: properties: preset: type: string title: Preset description: The preset. gpu: type: string title: Gpu description: Its GPU. gpus: type: integer title: Gpus description: GPUs per machine. seconds_low: type: number title: Seconds Low description: Fast end of the whole job on this preset. seconds_typical: type: number title: Seconds Typical description: Typical whole job on this preset. seconds_high: type: number title: Seconds High description: Slow end on this preset. usd_low: anyOf: - type: number - type: 'null' title: Usd Low description: Cost at `seconds_low` (whole machine). usd_high: anyOf: - type: number - type: 'null' title: Usd High description: Cost at `seconds_high`. credits_low: anyOf: - type: number - type: 'null' title: Credits Low description: Credits at `seconds_low`. credits_high: anyOf: - type: number - type: 'null' title: Credits High description: Credits at `seconds_high`. speedup: type: number title: Speedup description: >- Wall-time speed against the main estimate (2.0 = done in half the time). type: object required: - preset - gpu - gpus - seconds_low - seconds_typical - seconds_high - usd_low - usd_high - credits_low - credits_high - speedup title: MachineEstimateAlternative MachineEstimateRecommendation: properties: preset: type: string title: Preset description: The recommended preset. reason: type: string title: Reason description: One sentence to tell the user. type: object required: - preset - reason title: MachineEstimateRecommendation ErrorBody: properties: type: $ref: '#/components/schemas/ErrorType' description: Stable category to branch on. code: type: string title: Code description: >- Stable machine code; never renamed once published. An open set: x-voyager-errors lists the API's codes, and a refusal passed through from a model or /v1/machines may carry another; branch on type for a code you don't know. x-extensible-enum: - invalid_request - invalid_input - content_policy - upstream_unavailable - input_too_large - rate_limited - queue_full - model_unavailable - model_not_found - insufficient_credits - paid_plan_required - model_not_in_plan - model_access_required - outcome_unknown - expired - not_found - conflict - forbidden - internal_error - catalog_unavailable - catalog_invalid - billing_unavailable - no_voyager_seat - credits_reloading - cast_not_supported - voice_cloning_unavailable - too_many_references - input_too_long - payload_too_large - upload_too_large - intake_full - invalid_url - fetch_failed - unsupported_file - invalid_api_key - idempotency_conflict - idempotency_in_flight - invalid_idempotency_key - invalid_cursor - invalid_webhook_url - method_not_allowed - no_eligible_model - cap_unverifiable - decision_expired - decision_mismatch - decision_price_changed - account_unavailable - plan_required_for_faces - version_conflict - slug_taken - already_referenced - asset_in_use - upload_incomplete - cancel_unsupported - unsupported_cast_version - cast_version_required - cast_empty_package - cast_selection_invalid - cast_not_found - cast_version_mismatch - cast_capacity_exceeded - cast_images_required - cast_prompt_too_long - cast_plan_changed - unsupported_model - invalid_job_id - voice_required - observation_timeout - reference_unavailable - queue_timeout - reference_missing message: type: string title: Message description: For developers. Not localized. doc_url: type: string title: Doc Url description: https://docs.voyager.so/api/errors# request_id: anyOf: - type: string - type: 'null' title: Request Id description: Also in the X-Request-ID header; quote it to support. retryable: anyOf: - type: boolean - type: 'null' title: Retryable description: Whether the same request can succeed later. retry_after_ms: anyOf: - type: integer - type: 'null' title: Retry After Ms description: How long to wait before retrying. param: anyOf: - type: string - type: 'null' title: Param description: >- The request field at fault, as a path (e.g. input.resolution); set on invalid_input. loc: anyOf: - items: type: string type: array - type: 'null' title: Loc description: >- param as a path of parts (e.g. ["input", "resolution"]); set whenever param is. details: anyOf: - additionalProperties: true type: object - type: 'null' title: Details description: Code-specific detail, e.g. upgrade_url on a billing wall. type: object required: - type - code - message - doc_url title: ErrorBody ErrorType: type: string enum: - invalid_request - authentication - permission - not_found - conflict - rate_limited - idempotency_conflict - unprocessable - upstream_error - internal_error title: ErrorType description: Closed set of high-level categories SDKs branch on. headers: X-Request-ID: description: This request's id (also error.request_id). schema: type: string X-RateLimit-Limit: description: >- Requests allowed per 60 seconds in this bucket (120 writes or 600 reads per minute per key). schema: type: integer X-RateLimit-Remaining: description: Requests left in this window. schema: type: integer X-RateLimit-Reset: description: Seconds until the window resets. schema: type: integer Retry-After: description: Seconds to wait before retrying. schema: type: integer securitySchemes: API Key: type: http description: API key from Settings > Developer > REST API scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.