Skip to main content
POST
Typescript (SDK)

Authorizations

Authorization
string
header
required

API key in the format: Bearer {api_token}

Headers

Idempotency-Key
string

Makes this write safe to retry: a repeat with the same key replays the first response instead of creating a second resource. Scoped to the account, remembered for 24 hours; reusing a key with a different payload is an error.

Maximum string length: 255

Body

application/json
model
string
required

A quality tier (fast, balanced, quality) or any fal.ai video endpoint id. Prefer a tier — it tracks the best current model for that price point. Required: video bills per second, so there is no default. GET /v1/videos/models maps tiers to ids with live pricing.

Examples:

"fast"

"balanced"

"quality"

"fal-ai/veo3.1/lite"

"minimax/h3-max/text-to-video"

"google/gemini-omni-flash/v1.1/text-to-video"

"fal-ai/veo3.1"

input
object
required

Model-specific input, forwarded to fal verbatim. prompt is required.

Response

Generation job queued

id
string
required
object
string
required
type
string
required
status
enum<string>
required
Available options:
queued,
processing,
completed,
failed,
cancelled
model
string
required
progress
integer
required
input
object
required
result
object | null
required
error
string | null
required
error_code
string | null
required
credits_used
integer | null
required
provider_request_id
string | null
required
created_at
string<date-time>
required
started_at
string<date-time> | null
required
completed_at
string<date-time> | null
required