Seedance 2.0
Seedance 2.0. Image-to-video and Text-to-video with synchronized audio.
ByteDance$0.13 / secondtext-to-videoaudio-syncbytedance
Tier
Capability
Est. cost$0.65$1 ≈ 7 seconds of video.
Example output
$0.13/ second
$0.13 per second. $1 ≈ 7 seconds of video.
Pay only for successful generations. No idle, no minimums, no per-seat.
API
Wire it up.
Endpoint
POST https://api.tryinfer.com/v1/inference/seedance-2.0-pro/text-to-videorequest
curl https://api.tryinfer.com/v1/inference/seedance-2.0-pro/text-to-video \
-H "Authorization: Bearer $INFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "an octopus excitedly invites its friends to a coral-reef football game"
}
}'
Parameters
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
| seed | integer | — | — | — |
| audio | boolean | — | false | — |
| prompt | string | Yes | — | — |
| resolution | string | — | 720p | 720p1080p |
| aspect_ratio | string | — | 16:9 | 16:99:161:1 |
| duration_seconds | integer | — | — | 510 |
Authenticate with a bearer token. Get an API key →
Further reading
From the Infer content directory.
GuidesFal vs Replicate vs Infer: which platform in 2026Fal wins on latency, Replicate on catalog depth, Infer on multimodal price. This is Infer's own blog comparing itself, so here's the honest breakdown.GuidesHow AI video leaderboards actually work (and why they disagree)Elo, Bradley-Terry math, and dimension scoring, explained with a real example: the same model ranked #3 on one snapshot and #6 on another, 83 days apart.GuidesHow to prompt Seedance 2.0: camera, lighting, audioSeedance 2.0 Pro rewards director-style prompts: subject, camera move, lighting, and audio intent in one line. Ten worked templates and what fails.