Skip to main content
POST
Estimate the price of an image-to-video animation request
Estimate the cost of a video animation (image-to-video) job before submitting it.

Reference inputs

Send counts matching the planned Video Animation request. A quote does not require file uploads. The source image does not count as a reference image. Exactly 2 reference images adds no surcharge. Reference audio adds no surcharge.
Multipliers do not compound: 4 reference images and 1 reference video applies ×3, not ×6. Generation limits still depend on the selected model — check Model Selection before choosing reference counts.
A successful quote does not validate the model’s reference-file limits. For example, the price endpoint accepts 4 reference images and 1 reference video for MiniMaxH3_33B_Turbo_INT8, but that model currently permits only 3 reference files in total. Check max_ref_images, max_ref_videos, and max_ref_files before generation.

Authorizations

Authorization
string
header
required

Sanctum personal access token, sent as Authorization: Bearer <token>. The token is opaque — it carries no claims and no embedded expiry, so do not attempt to decode it. Issue and revoke tokens from your account dashboard.

Headers

Accept
enum<string>
default:application/json
required
Available options:
application/json

Body

application/json

Image to video price calculation parameters

Every example in this schema is a working set for the model example shown — they are not defaults and not portable. Sizes, step counts, frame counts and frame rates are all per-model: read info.limits and info.defaults for the model you actually intend to use from GET /api/v2/models. Substituting a different model while keeping these values is the most common source of a 422.

width
integer
required

Width of the generated video in pixels. The accepted range is model-specific — read info.limits.min_width/max_width and min_height/max_height for your model from GET /api/v2/models. Some models also publish dimension_multiple or resolution_step: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. max_pixels and max_ratio, where present, cap total area and aspect ratio on top of the per-side bounds.

Example:

512

height
integer
required

Height of the generated video in pixels. The accepted range is model-specific — read info.limits.min_width/max_width and min_height/max_height for your model from GET /api/v2/models. Some models also publish dimension_multiple or resolution_step: values are snapped DOWN to that grid before validation, so an off-grid size is silently reduced rather than rejected. max_pixels and max_ratio, where present, cap total area and aspect ratio on top of the per-side bounds.

Example:

512

frames
integer
required

Number of video frames to generate. The accepted range is model-specific — read info.limits.min_frames/max_frames for your model from GET /api/v2/models; a value outside it is rejected with 422.

Example:

120

fps
integer
required

FPS of the generated video. The model dictates the value: read info.defaults.fps for your model from GET /api/v2/models. Where min_fps equals max_fps that is the only accepted value; anything outside the range is rejected with 422.

Example:

30

model
string
required

The model to use for video generation. Available models can be retrieved via the GET /api/v2/models endpoint.

Example:

"Ltxv_13B_0_9_8_Distilled_FP8"

steps
integer

Number of inference steps. Bounded by info.limits.min_steps / max_steps from GET /api/v2/models (1–100 when the model declares none). Required when the model declares info.features.supports_steps: true; optional when the flag is absent. When the model declares supports_steps: false the value is accepted and dropped — it is neither forwarded to the worker nor priced.

Example:

1

ref_images_count
integer
default:0

How many ref_images the generation request will carry. More than 2 reference images multiplies the price by 2. The source image of an img2video request is not a reference image and does not count, so exactly 2 is still unmultiplied. Send the count here rather than the files — a quote never requires an upload.

Required range: 0 <= x <= 9
Example:

4

ref_videos_count
integer
default:0

How many ref_videos the generation request will carry. Any reference video multiplies the price by 3. The two surcharges do not compound: the highest applicable multiplier wins, so 4 reference images plus a reference video is x3, not x6. Reference audio carries no surcharge.

Required range: 0 <= x <= 1
Example:

1

ref_audios_count
integer
default:0

How many ref_audios the generation request will carry. No surcharge; accepted so the quote applies the same per-model reference limits (info.limits.max_ref_*, info.features.supports_*_refs) as the generation request. The example set here belongs to the model example shown.

Required range: 0 <= x <= 3
Example:

0

Response

Calculated price for img2video inference.

data
object