Skip to main content
POST
Estimate a generation's cost

Authorizations

Authorization
string
header
required

Your organization's API key, from Settings → MCP. Authorization: Bearer crl_sk_live_…

Body

application/json
account_id
string<uuid>
required

Required. Generate as this creator — inherits their look, voice and persona, and the run lands in their API project.

tool
enum<string>

The tool to run. Preferred over stage.

Available options:
ugc-video,
reshoot,
short-clip,
scene-video,
motion-control,
hook-captions,
merge-clips,
photo-edit,
text-to-photo,
add-audio,
lipsync,
change-voice,
text-to-speech,
dialogue
stage
string

Lower-level escape hatch when you want to address a stage directly.

model
enum<string>

Override the tool's default model. Must belong to the tool's stage.

Available options:
nano-banana-pro,
nano-banana-2-text-to-image,
gpt-image-v2-text-to-image,
nano-banana-pro-edit,
nano-banana-2-edit,
bytedance-seedream-v4-5-edit,
gpt-image-v2-edit,
bytedance-seedance-2-5-image-to-video,
bytedance-seedance-2-0-image-to-video,
bytedance-seedance-2-0-image-to-video-fast,
xai-grok-imagine-video-1-5-preview-image-to-video,
minimax-h3-max-image-to-video,
minimax-h3-max-turbo-image-to-video,
kling-v3-4k-image-to-video,
kling-v3-pro-image-to-video,
kling-v3-standard-image-to-video,
kling-o3-standard-image-to-video,
google-gemini-omni-flash-image-to-video,
veo-3-1-lite-text-to-video,
veo-3-1-lite-first-last-frame-to-video,
veo3-1-text-to-video,
veo3-1-first-last-frame-to-video,
veo3-1-first-last-frame-to-video-fast,
veo3-1-reference-to-video,
flux-3-text-to-video,
flux-3-image-to-video-timestamped,
bytedance-seedance-2-0-reference-to-video,
bytedance-seedance-2-0-mini-reference-to-video,
bytedance-seedance-2-0-reference-to-video-fast,
bytedance-seedance-2-5-reference-to-video,
xai-grok-imagine-reference-to-video,
google-gemini-omni-flash-reference-to-video,
kling-v3-standard-motion-control,
hook-write,
caption-burn,
short-clip,
bytedance-seedance-2-0-text-to-video,
minimax-h3-max-text-to-video,
minimax-h3-max-turbo-text-to-video,
sync-3-lipsync,
sync-lipsync-v2-pro,
ffmpeg-api-merge-audio-video,
elevenlabs-zrm-text-to-speech,
elevenlabs-zrm-text-to-dialogue,
change-voice,
merge-clips,
scene-seedance-2-5,
reshoot-seedance-2-0,
reshoot-seedance-2-5,
scene-seedance-2-0,
scene-seedance-2-0-mini,
scene-kling-o3-pro-reference,
scene-seedance-2-0-fast,
scene-kling-o3-standard-reference,
scene-kling-o3-pro-edit,
scene-kling-o3-standard-edit
prompt
string

What to create. Required by most models.

avatar_id
string

The avatar the run renders with (from GET /v1/avatars): its face goes into the model's character slot and its voice is the default for any voice parameter. Must belong to your workspace (404 otherwise). Omit to use the account's default avatar.

inputs
object

Slot key → asset id(s) or public https URL(s), per the model's inputs. A URL is adopted as an asset automatically.

params
object

Model parameters. Validated against the model's schema — an unknown key is a 400.

count
integer

Alternatives to produce, up to the model's max_count. Image models only; video is always one take.

Required range: 1 <= x <= 4
source_url
string<uri>

For a tool with accepts_source_url (today short-clip): the video LINK to work from, instead of uploading it. Pass this OR the source asset in inputs, never both. The run is priced off the link's real length.

include_account_avatar
boolean
default:true

The creator's avatar is added to the model's character slot so they stay recognisable across runs. Set false when the output must NOT contain the creator (a product shot on their account, a scene without them).

Response

The estimate.

object
enum<string>
Available options:
cost_estimate
model
string
stage
string
count
integer
duration_sec
number

The length the estimate billed: the chosen output duration, or the source media's length for the models billed per second of source.

credits
number
credit_balance
number
sufficient
boolean