Generate a video from a text prompt with Seedance 2.5 Flash. Submit a generation task, then retrieve the finished video using the task ID.
Developer API pricing
Provider: SeeAPI
USD estimate: $0.0037 / credit · Estimated equivalent, not an additional charge.
480p: 24.69 credits/sec (≈ $0.093/sec)
720p: 54.72 credits/sec (≈ $0.21/sec)
/v1/generationsA new, stable key for each generation request. Reuse it only when retrying the same request body.
order-20260818-001Identifies the model. Use seedance-2-5-flash for this request.
seedance-2-5-flashseedance-2-5-flashseedance-2-5-flashSelects the generation mode. Use text-to-video for this request.
text-to-videotext-to-videotext-to-videoAn optional public provider ID. Omit this field to use the endpoint’s default, seeapi.
seeapiseeapiseeapiModel parameters for this endpoint. Pass the fields below inside this object.
Provider parameters
seeapiDefault ProviderDescribe the subject, action, camera movement, and details you want in the generated video.
A red ball rolls slowly across a white table. The camera tracks it from the side.Sets the shape of the output frame. Use adaptive to let the model choose the aspect ratio.
16:94:31:13:49:1621:9adaptiveadaptiveSet the output duration to an integer from 4 to 30 seconds. If omitted, it defaults to 5 seconds.
456789101112131415161718192021222324252627282930min: 4max: 305Sets the output resolution. This value selects the billing rate.
480p720p720pSet to true to generate synchronized audio with the video. Set to false for silent output.
trueSets the output video container.
mp4movmp4Requests the final frame as an additional image when available. Use it as the starting image for a follow-up clip.
falseEnables the content safety check for this generation.
falseLets the model use web search for context when interpreting the prompt.
falseAn absolute HTTPS URL that receives the terminal generation Webhook.
https://client.example.com/webhooks/seeapiTask record returned when a request is accepted or replayed.
Save this task ID and use it to query the generation status.
task_xxxModel ID used for this generation.
seedance-2-5-flashGeneration mode used for this task.
text-to-videoPublic provider ID used for this task.
seeapiseeapi: SeeAPIseeapiCurrent task status. Query the task until it succeeds or fails.
processingprocessingEstimated public credits. Values can include up to three decimal places.
273.6Consumed public credits, with up to three decimal places.
0Refunded public credits, with up to three decimal places.
0Timestamp when the task was created.
2026-08-18T10:00:00ZTimestamp of the most recent task update.
2026-08-18T10:00:00ZWhether this response is an idempotent replay of an earlier request.
falseTask record returned when a request is accepted or replayed.
Save this task ID and use it to query the generation status.
task_xxxModel ID used for this generation.
seedance-2-5-flashGeneration mode used for this task.
text-to-videoPublic provider ID used for this task.
seeapiseeapi: SeeAPIseeapiCurrent task status. Query the task until it succeeds or fails.
processingprocessingEstimated public credits. Values can include up to three decimal places.
273.6Consumed public credits, with up to three decimal places.
0Refunded public credits, with up to three decimal places.
0Timestamp when the task was created.
2026-08-18T10:00:00ZTimestamp of the most recent task update.
2026-08-18T10:00:00ZWhether this response is an idempotent replay of an earlier request.
falseInvalid JSON, parameters, Schema, or API Policy
Invalid API Key or authentication failed
Insufficient credits
The current request is not allowed
Model, Endpoint, or task not found
Idempotency conflict or the same request is still being created
Request body is too large
Too many requests
Service temporarily unavailable
After submitting a task, use the unified query endpoint to check progress and retrieve results:
Save the returned generation ID. When the task succeeds, retrieve the video from result.assets. If it fails, read the error before submitting a new request.
Manage the secret used to verify generation webhook signatures. Callback URLs are supplied when you create each generation.
Callback URL per generation.
const response = await fetch("https://api.seeapi.com/v1/generations", {
method: "POST",
headers: {
"Authorization": "Bearer YOUR_API_KEY",
"Idempotency-Key": "order-20260818-001",
"Content-Type": "application/json"
},
body: JSON.stringify({
"model": "seedance-2-5-flash",
"endpoint": "text-to-video",
"provider": "seeapi",
"input": {
"prompt": "A red ball rolls slowly across a white table. The camera tracks it from the side.",
"aspect_ratio": "adaptive",
"duration_seconds": 5,
"resolution": "720p",
"generate_audio": true,
"output_format": "mp4",
"return_last_frame": false,
"nsfw_checker": false,
"web_search": false
},
"callback_url": "https://client.example.com/webhooks/seeapi"
})
});
const result = await response.json();{
"generation": {
"id": "task_xxx",
"model": "seedance-2-5-flash",
"endpoint": "text-to-video",
"provider": "seeapi",
"status": "processing",
"estimated_credits": 273.6,
"consumed_credits": 0,
"refunded_credits": 0,
"created_at": "2026-08-18T10:00:00Z",
"updated_at": "2026-08-18T10:00:00Z"
},
"idempotent": false
}