AI Video/Estimate cost
Estimate cost
GET/api/v1/ai_video/cost
Estimate the credits a generation will cost before submitting, using the same formula as the actual charge. Omit resolution to price the model default.
Beta: available to any account with an active paid subscription; standard per-key rate limits apply.
Query parameters
model_idstringRequired
Model to price for. Use an id from GET /api/v1/ai_video/models, e.g.
seedance-2.0.duration_secnumberRequired
Clip length in seconds to price. Use an allowed model duration; for V-Character 5.0 Pro auto/video-edit requests, pass the resolved reference duration (2–15s).
resolutionstring | nullOptional
Output resolution to price, e.g.
480p / 720p / 1080p / 4k. Allowed values vary by model; omit to use the model default.reference_video_duration_secnumberOptionalDefault
0Sum of reference-video durations, capped per video at 15s (Seedance 2.0 series) or 30s (
seedance-2.5, seedance-2.5-flash, kling-4.0). All Seedance models and kling-4.0: reference seconds up to half the output duration are free; only excess seconds cost 60% of the output rate. V-Character 5.0 Pro: any positive value doubles the generation second rate, once per task. For estimation only; actual charge uses server-measured durations.generate_audioboolean | nullOptional
Whether a native audio track is requested. Accepted for parity with the create request; audio never changes the price.
Headers
X-API-KeystringRequired
Your VisionStory API key (
sk-vs-...), kept server-side. Create one at OpenApi (Pro plan and up).Response
200Successful Response
Successful calls return a standard envelope: the endpoint payload under data (its fields are documented below), plus a message string ("success") and an ISO 8601 server_time.
Response fields (
data)base_creditintegerOptionalDefault
0Generation credits rounded up. With reference-video pricing, the surcharge is the rounded total minus this amount.
reference_videoReferenceVideoCostDto | nullOptional
creditintegerRequired
Estimated credits the generation will cost with the given parameters. Uses the same formula as the actual charge.
Errors
All error responses share one JSON envelope: an error object with a numeric code, a human-readable message, an optional details string, and an optional hint giving an actionable next step (handy for AI agents).
errorErrorDetailRequired
Error payload returned with every non-2xx response. Present only on failure; successful calls use the standard success envelope instead.