18Models
DocsModelPricingUse CasesLog inTry for Free
Try for FreeLog in

Seedance 2.5 API — token-settled, NSFW allowed

NSFW allowed under the published Content Policy · USD prices from the live price list · One API key for every model

18models provides Seedance 2.5 in six modes — text-to-video, first-frame and first + last-frame image-to-video, omni-reference (images, video and audio together), video edit and video extend — at 480p or 720p and 4–30 seconds. Billing is by output tokens at $10.70 per million (about $0.23 per second at 720p; $6.40 per million when video is supplied as input), 2.5% below Segmind's list price as of 2026-08-19, with NSFW output permitted under our content policy.

Modes and model IDs

ModeModel IDInputs & key parameters
Text-to-videoseedance-2.5-t2v-uncensoredprompt; 480p/720p, 4–30 s or -1 auto, ratio adaptive · 16:9 · 4:3 · 1:1 · 3:4 · 9:16 · 21:9
Image-to-video · first frameseedance-2.5-firstframe-uncensored1 image + prompt
Image-to-video · first + last frameseedance-2.5-firstlast-uncensored2 images + prompt
Omni-referenceseedance-2.5-reference-uncensoredup to 30 images, 10 videos, 10 audio clips (≤30 s of video and of audio in total)
Video editseedance-2.5-edit-uncensored1–10 clips (4–30 s each) + prompt; inputs must not contain real people
Video extendseedance-2.5-extend-uncensored1–10 clips extended in sequence + prompt; inputs must not contain real people

Every mode uses the same request shape: model + prompt + media arrays (images / videos / audios / files as public HTTPS URLs) + params. Full field tables: API docs.

Prices (USD, base list)

ModelVariantPrice
seedance-2.5-edit-uncensored480p$0.55300/video (from)
seedance-2.5-edit-uncensored720p$1.24/video (from)
seedance-2.5-extend-uncensored480p$0.55300/video (from)
seedance-2.5-extend-uncensored720p$1.24/video (from)
seedance-2.5-firstframe-uncensored480p$0.10300/s
seedance-2.5-firstframe-uncensored720p$0.23100/s
seedance-2.5-firstlast-uncensored480p$0.10300/s
seedance-2.5-firstlast-uncensored720p$0.23100/s
seedance-2.5-reference-uncensored480p · image/audio references only$0.10300/s
seedance-2.5-reference-uncensored720p · image/audio references only$0.23100/s
seedance-2.5-reference-uncensored480p · with video reference$0.55300/video (from)
seedance-2.5-reference-uncensored720p · with video reference$1.24/video (from)
seedance-2.5-t2v-uncensored480p$0.10300/s
seedance-2.5-t2v-uncensored720p$0.23100/s

Base list prices from the live price list (/pricing · pricing.json); the effective price for your key is returned by GET /ent/v2/prices. Cost is reserved at submit and settled on completion — failed tasks are refunded in full.

Example request

POST https://api.18models.ai/ent/v2/generate
Authorization: Bearer sk-…
Content-Type: application/json
Idempotency-Key: <stable-request-id>
{
  "model": "seedance-2.5-t2v-uncensored",
  "prompt": "Handheld shot, a couple dancing close in a dim kitchen, soft focus, film grain",
  "params": { "resolution": "720p", "ratio": "16:9", "duration": 6 }
}

The response is HTTP 202 with a task_id; poll GET https://api.18models.ai/ent/v2/tasks/{task_id} (back off 2 s → 5 s) until status is success or failed, then read result_urls. Ready-made client code: docs → Build with AI or the Agent Skill.

What is allowed

NSFW output is permitted under the 18models Content Policy: fictional adult content, including explicit sexual content, is allowed; content involving minors (in any style) or real, identifiable people is prohibited absolutely and screened on both input and output. Upstream providers apply their own checks in addition to ours — a task rejected upstream fails and is refunded automatically.

  • Token settlement: the per-second price shown at submit is an estimate; the task settles on the provider's completion_tokens ($10.70/M without video input, $6.40/M with) and any reservation difference is refunded.
  • Provider input check: video edit / extend inputs that appear to contain a real person are rejected at submission (InputVideoSensitiveContentDetected.PrivacyInformation) and refunded. Images for first-frame / first-last / reference modes are not subject to that check.
  • Fictional adults only under the 18models Content Policy; the upstream model applies its own output checks in addition to ours.

FAQ

How is Seedance 2.5 billed on 18models?

By output tokens: $10.70 per million tokens without video input, $6.40 per million with video input. The per-second price shown at submit is an estimate; the task settles on the provider's reported completion_tokens and any difference is refunded.

Does Seedance 2.5 on 18models allow NSFW content?

Fictional adult content is permitted under the 18models Content Policy. Note the provider's own input check: video edit and extend inputs must not contain a real person, or the task fails at submission and is refunded.

Is 18models cheaper than Segmind for Seedance 2.5?

As of 2026-08-19, 18models lists $10.70 per million output tokens versus Segmind's $10.97 — about 2.5% lower — for the same model.

What resolutions and durations does Seedance 2.5 support?

480p and 720p; 4–30 seconds, or -1 to let the model choose the duration. Omni-reference accepts up to 30 images, 10 videos and 10 audio clips per request.

Related

  • 18models vs Segmind (Seedance pricing)
  • Wan 2.7 video
  • All models & prices
  • Pricing
  • API docs
  • Content Policy
Try it on your own prompts. Run this model in the playground, or get an API key and integrate in an afternoon.
Open playgroundGet your API key
18Models

High-fidelity AI video generation built for platforms and creators who push boundaries.

All systems operational
Product
DocsPricingAll modelsPlaygroundNSFW policy trackerAPI StatusChangelog
Models
Wan 2.7 videoWan 3.0 videoHappyHorseSeedance 2.5Qwen-Image 3.0Z-Image TurboWan 2.7 image
Solutions
AI companion appsAdult gamesCreator platformsCharacter consistencyMigrate from Novita
Compare
vs Novitavs WaveSpeedvs fal.aivs Replicatevs CivitAIvs ModelsLabvs Segmind
Legal
Privacy PolicyTerms of ServiceContent PolicyCookie Policy
© 2026 18models.ai. All rights reserved.
TLS in transit · Hashed API keys · Operational audit logs