Skip to content

estimate_forge_price

Estimate the Creative Units price of a forge run before executing it.

Requires either a `base_model_id` or at least one reference set; passing neither is an error.
Prices through the same reference-set translation and model selection as `execute_forge`, so
the returned price matches what execution charges for identical inputs. Executes nothing.

For forge lifecycle guidance, call get_forge_instructions.

Parameters

ParameterTypeDefaultDescription
base_model_idstringBase model to price, given as an id (e.g. flux-dev), display name, or community alias. Not required when passing reference sets — a model is then auto-picked from them. Required otherwise.
reference_setsForgeReferenceSetInput[][]Reference Sets the run will attach. Required when no base_model_id is given.
set_idrequiredstring (uuid)Reference Set ID, from `list_reference_sets`.
weightnumber0–21Weight for the set's LoRA adapter when one applies. 1.0 = as trained; lower weakens, higher over-applies. Ignored for sets applied as reference images or prompt text.
modalityenumOutput modality: image, video, three_d, or audio. Used to disambiguate reference-set translation; inferred from the reference sets when omitted.
One of: text, image, audio, video, three_d, playable
widthinteger>0Output width in pixels. Pass both width and height whenever the output must have a specific aspect ratio: with either one absent and an init image, editing reference, or first frame attached, the output geometry is taken from that file rather than from a model default.
heightinteger>0Output height in pixels. Pass both width and height whenever the output must have a specific aspect ratio: with either one absent and an init image, editing reference, or first frame attached, the output geometry is taken from that file rather than from a model default.
batch_sizeinteger1–164Number of outputs to estimate price for (1-16).
duration_secondsnumber>0Output length in seconds — video clip length, or audio clip length for models whose duration_seconds_min / duration_seconds_max say they take one.
promptstringText prompt. Needed for CHARACTER_COUNT pricing models.
generate_audiobooleanGenerate audio with video.
upscale_rationumberUpscale factor (e.g. 2.0, 4.0).
remove_backgroundbooleanRemove the background — pass it here whenever the execute call will, so the estimate reflects the same run.
cameraForgeCameraInputCamera view change the execute call will pass — include it here for parity, so the estimated model can be checked for camera_transform support before money is spent.
yaw_degreesnumber-360–360Orbit horizontally around the subject, in degrees: 90 = right side view, 180 = back view, 270 (or -90) = left side view.
pitch_degreesnumber-30–90Camera elevation in degrees: positive looks down (90 = top-down), negative looks up (-30 is the lowest supported angle).
roll_degreesnumberBank around the viewing axis in degrees, clockwise positive. Natively camera-capable models ignore roll.
distance_deltanumberDolly out (positive) / in (negative), in scene units; ~5 spans wide shot to close-up.
fov_delta_degreesnumberField-of-view change in degrees: positive widens (zoom out), negative narrows. Alternative to distance_delta.
qualityenumQuality level.
One of: low, medium, high
use_ta_posebooleanDeprecated: use pose_mode. Legacy rig-ready-pose toggle for 3D.
pose_modeenumRest pose for a character mesh: A_POSE or T_POSE. Support varies by model.
One of: A_POSE, T_POSE
include_texturesbooleanInclude textures in 3D output.
quad_meshbooleanGenerate quad mesh.
pbr_materialsbooleanGenerate PBR materials.
low_polybooleanGenerate low-poly mesh.
generate_partsbooleanGenerate separate parts.
detailed_geometrybooleanGenerate denser, more detailed geometry. Costs extra and only some 3D models support it.
export_uvbooleanSet false to omit UV coordinates from the 3D output.
compress_geometrybooleanReturn a geometry-compressed mesh. Only some 3D models support it.
face_limitintegerFace/polygon limit for 3D mesh.
workspace_idrequiredstring (uuid)The user's workspace id.