Seedance 2.5 Flash Spicy API on Siray AI: Pricing, Endpoints and Tested Prompts
The Seedance 2.5 Flash Spicy API gives you ByteDance's Seedance 2.5 Flash video model through Siray AI endpoints intended for mature creative work. It costs about $0.068 per second at 480p and $0.151 per second at 720p, for clips of 4 to 30 seconds with optional audio. It suits fast drafts, high-volume social clips and adult-audience projects.
Key takeaways
- Three Spicy endpoints: text-to-video, image-to-video (first frame, optional last frame) and reference-to-video with up to 10 images, 5 videos and 5 audio files.
- Token-based pricing: $0.007 per 1K tokens. A 5-second 720p clip costs about $0.76 and a 30-second 720p clip about $4.54.
- Fast in our tests: seven clips of 5 to 10 seconds each finished in 72 to 100 seconds from submit to result, including five submitted at the same time.
- 480p and 720p only: there is no 1080p tier. Use the full Seedance 2.5 when you need higher resolution.
- Output moderation still applies: one of our SFW prompts (a neon city street) was rejected with a copyright-related policy error, and that task was not billed.
What is Seedance 2.5 Flash?
Seedance 2.5 Flash is a faster, cheaper tier of ByteDance's Seedance 2.5 video model. ByteDance's cloud unit Volcano Engine announced it on November 12, 2026, and API access opened on November 15, 2026, according to Pandaily and other launch coverage. ByteDance says Flash generates video about twice as fast as Seedance 2.5 at roughly 34% lower cost, with output close to the flagship. We could not open ByteDance's own Flash pages to confirm these figures, so treat them as reported vendor claims.
The flagship Seedance 2.5 is described by ByteDance Seed as "a next-generation audio-video joint generation model, built for 30-second storytelling", with up to 30 seconds per generation, more reliable editing and better understanding of reference videos. Flash keeps the 30-second length and native audio but, per launch coverage, drops to 720p and accepts fewer references.
Known limits. Flash outputs only 480p and 720p. Siray AI's reference endpoint accepts up to 10 images, 5 videos and 5 audio files, fewer than the flagship's reported 50 references. ByteDance's own speed claims have not been independently benchmarked; our timings below are one data point.
What does Spicy mean?
Spicy is a Siray AI catalog label, not a separate ByteDance model. The Siray AI API reference says the variant "supports mature and boundary-pushing creative content for production workflows." On Siray AI, Seedance 2.5 Flash is currently available only as Spicy endpoints.
Fewer restrictions do not mean no rules. Siray AI's policy for uncensored generation says all content "must depict legal adult (18+) individuals only", and illegal content is refused. Don't use a real person's likeness without their consent, and follow your local laws and the rules of the platforms where you publish. Every example in this guide is SFW. For an adult-oriented walkthrough, see Seedance 2.5 Spicy Slow Dance: Direct Two Adult Partners.
Seedance 2.5 Flash Spicy endpoints on Siray AI
| Model ID | Task | Required inputs | Optional inputs |
|---|---|---|---|
bytedance/seedance-2.5-flash-t2v-spicy |
Text-to-video | prompt, duration, size, aspect_ratio |
audio_enable |
bytedance/seedance-2.5-flash-i2v-spicy |
Image-to-video | prompt, image, duration, size, aspect_ratio |
end_image, audio_enable |
bytedance/seedance-2.5-flash-ref2v-spicy |
Reference-to-video, edit, extend | prompt, duration, size, aspect_ratio |
images (≤10), videos (≤5), audios (≤5), task_type, audio_enable |
Shared values on all three endpoints:
duration: any whole number from 4 to 30. The reference endpoint also accepts-1, which lets the model choose the length.size:480por720p.aspect_ratio:adaptive,16:9,4:3,1:1,3:4,9:16or21:9.task_type(reference endpoint only):reference,auto,editorextend.- Images can be URLs or data URLs.
Seedance 2.5 Flash Spicy pricing on Siray AI
All three endpoints are billed by output tokens at $0.007 per 1K tokens. Siray AI's pricing note gives the formula: height × width × (input duration + output duration) × 24 ÷ 1024. In practice that works out to these prices for text-to-video, image-to-video and reference-to-video without video input:
| Duration | 480p | 720p |
|---|---|---|
| 5 seconds | $0.34 | $0.756 |
| 10 seconds | $0.68 | $1.512 |
| 15 seconds | $1.02 | $2.268 |
| 30 seconds | $2.04 | $4.536 |
| Per second | ≈ $0.068 | ≈ $0.151 |
When you pass reference videos, the rate drops to $0.0043 per 1K tokens, but the input video's length is added to the token count. Siray AI lists a range for these jobs; for example, a 5-second 720p reference job with video input costs $0.84 to $3.25 depending on the input.
Worked examples:
- A 5-second 720p draft: $0.756. Twenty drafts cost $15.12.
- A 15-second 9:16 social clip at 480p: $1.02.
- A full 30-second 720p spot: $4.536.
Prices were read from the Siray AI pricing API on November 16, 2026, with no discount active. Check the Seedance 2.5 Flash t2v Spicy model page for live prices. In our tests, actual charges matched the formula within about 1%: a 5-second 720p clip used 108,900 tokens ($0.762).
Concept video generated with Seedance 2.5 Flash on Siray AI.
Quickstart: call the Seedance 2.5 Flash Spicy API
Generation is asynchronous. Submit a task to get a task_id, then check it every 3–5 seconds. When the status is SUCCESS, download the video from data.outputs.
1. Submit a task
curl -X POST https://api.siray.ai/v1/video/generations \
-H "Authorization: Bearer $SIRAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "bytedance/seedance-2.5-flash-t2v-spicy",
"prompt": "A slow cinematic drone push-in over a foggy pine forest at sunrise...",
"duration": 5,
"size": "720p",
"aspect_ratio": "16:9",
"audio_enable": true
}'
The response contains the task ID. In our tests it was at the top level of the response (task_id), not under data as the API reference shows, so read both places.
2. Poll until the task finishes
curl https://api.siray.ai/v1/video/generations/<task_id> \
-H "Authorization: Bearer $SIRAY_API_KEY"
status goes from IN_PROGRESS to SUCCESS or FAILURE. On success, data.outputs holds the MP4 URL and data.usage.completion_tokens shows the billed tokens. On failure, check fail_code and fail_reason.
For image-to-video, change model to bytedance/seedance-2.5-flash-i2v-spicy and add "image": "<URL or data URL>". For reference-to-video, use bytedance/seedance-2.5-flash-ref2v-spicy with "task_type": "reference" and "images": [...].
Concept video generated with Seedance 2.5 Flash on Siray AI.
Seedance 2.5 Flash prompt examples (tested)
We ran every example below on November 16, 2026 through the Siray AI API. Times are measured from submit to finish on the task record. Costs come from the billed tokens.
1. Drone camera move with ambient audio
A slow cinematic drone push-in over a foggy pine forest at sunrise. The camera starts high above the treetops, glides forward and gradually tilts down to reveal a narrow river winding through the valley, golden light breaking through the mist. Smooth, stable motion, no cuts. Natural ambient sound: soft wind, distant birdsong, the faint rush of water. No people.
Prompt for seedance 2.5 flash spicy
- Endpoint:
t2v-spicy, 5 s, 720p, 16:9,audio_enable: true - Time: 99 seconds · Cost: $0.762 · Output: 1280×720, 24 fps, with an audio track\
Video Generated by Siray ai
The push-in and the tilt down to the river came out exactly as written, with no jitter. Spelling out the start point, the motion and the reveal kept the camera move readable in five seconds.
2. Character action at 480p
Medium shot in a sunlit pottery studio. A woman in her early 30s with a linen apron and rolled-up sleeves centers wet clay on a spinning wheel, presses her thumbs into the middle and slowly pulls the walls of a bowl upward. Her hands stay on the clay the whole time; the bowl rises steadily as the wheel turns. Static camera at table height, shallow depth of field, warm afternoon light through a dusty window. Adults only, no children, teenagers, babies or minors.
Prompt for seedance 2.5 flash spicy
- Endpoint:
t2v-spicy, 8 s, 480p, 16:9, no audio - Time: 85 seconds · Cost: $0.541 · Output: 854×480, 24 fps
Video Generated by Siray ai
Her hands stayed on the clay for all eight seconds, which is where many video models fail. The clay grew into a tall vase rather than a bowl, so name the final shape more firmly if it matters. 480p is clearly softer, but it is enough to check motion before paying for 720p.
3. Three-shot sequence with sound
A three-shot sequence at a small seaside bakery at dawn, natural documentary look.
Shot 1 (wide): a baker in her 50s with grey hair tied back and a flour-dusted blue apron unlocks the wooden door of a whitewashed bakery by the harbor and steps inside.
Shot 2 (close-up): her hands shape a round loaf of dough on a floured wooden table, then score the top with a small blade.
Shot 3 (medium shot): she slides the loaf into a glowing brick oven with a long wooden peel and smiles as warm light falls on her face.
Keep the same woman, apron and bakery in every shot. Sound: seagulls outside, the creak of the door, the crackle of the oven fire. Adults only, no children, teenagers, babies or minors. No text, no logos.
Prompt for seedance 2.5 flash spicy
- Endpoint:
t2v-spicy, 10 s, 720p, 16:9,audio_enable: true - Time: 100 seconds · Cost: $1.518 · Output: 1280×720, with an audio track
Video Generated by Siray ai
All three shots appeared in order with clean cuts. The blue apron and grey hair matched across shots. Numbering shots and giving each a framing word (wide, close-up, medium) was enough to get the edit.
Our first version of this prompt, a man walking through a rainy neon-lit city, failed with OutputVideoSensitiveContentDetected.PolicyViolation and the message "the output video may be related to copyright restrictions." The prompt was SFW. Our guess is that busy signage triggered the copyright check. No tokens were reported for the failed task.
4. Image-to-video: animate a product photo
Animate this product photo. Steam begins to rise slowly from the mug and curls upward; soft morning light shifts gently across the table. The camera makes a slow, smooth orbit of about 20 degrees to the right around the mug. The mug itself stays still and keeps its exact shape, color and details. No hands, no people, no text.
Prompts for the video
- Endpoint:
i2v-spicy, 5 s, 720p,aspect_ratio: adaptive, one input image (data URL) - Time: 72 seconds · Cost: $0.766 · Output: 1178×786
Video Generated by Siray ai
The mug kept its shape, glaze and handle exactly, and the steam looked natural. The orbit was much smaller than 20 degrees. With adaptive, the output followed the input photo's ratio (1178×786) instead of a fixed 1280×720.
5. Reference-to-video: place a product in a location
Use image 1 as the location and image 2 as the product. A slow dolly shot across the bright salt flat from image 1 at golden hour; the ceramic mug from image 2 sits on a small wooden stool in the middle of the salt flat, keeping its exact shape and color. Warm wind moves thin clouds across the sky and the long shadow of the stool stretches toward the camera. Calm, minimal, editorial mood. No people, no text.
Prompts for the video
- Endpoint:
ref2v-spicy, 6 s, 720p, 16:9,task_type: reference, two input images - Time: 84 seconds · Cost: $0.914 · Output: 1280×720
Video Generated by Siray ai
Referring to inputs as "image 1" and "image 2" worked: the model took the location from one image and the mug from the other. The mug's colour and handle matched the reference. Camera movement was again gentler than asked.
Prompting tips for Seedance 2.5 Flash
- Ask for more camera motion than you want. In both image-driven tests, orbits and dollies came out smaller than written. Pure text-to-video followed camera directions closely.
- Number your shots. "Shot 1 (wide) … Shot 2 (close-up) …" produced clean cuts in a 10-second clip. Repeat the details that must stay the same in every shot.
- Name inputs by position. On the reference endpoint, "image 1 as the location, image 2 as the product" was enough to assign roles.
- Draft at 480p. A 480p clip costs 45% of the 720p price and shows whether motion and timing work.
- Keep busy signage out of SFW prompts. Neon signs and dense brand-like text may trigger the copyright check, as in our failed test.
- State adult ages and add "no children, teenagers, babies or minors". This is required by Siray AI's rules for Spicy endpoints and keeps results predictable.
When to use Seedance 2.5 Flash (and when not to)
Use it for:
- Fast drafts and A/B variants before a final render.
- High-volume social clips at 480p or 720p.
- Product clips from a photo or from reference images.
- Mature-themed creative work that needs a Spicy endpoint.
Look elsewhere when:
- You need 1080p or higher: use the full Seedance 2.5 or another model that offers 1080p.
- You need more than 10 reference images in one request.
- You need a non-Spicy endpoint for compliance reasons: the plain
bytedance/seedance-2.5-t2v,i2vandref2vendpoints are also on Siray AI.
For a reference-driven example with the full model, see Seedance 2.5 Museum Clips: Parallax Without Reshaping.
FAQ
How much does the Seedance 2.5 Flash Spicy API cost per second?
About $0.068 per second at 480p and $0.151 per second at 720p on Siray AI. Billing is $0.007 per 1K output tokens, so a 5-second 720p clip costs about $0.76 (prices checked November 16, 2026).
What is the difference between Seedance 2.5 Flash and Seedance 2.5?
Flash is ByteDance's faster, cheaper tier of Seedance 2.5. ByteDance says it is about twice as fast and about 34% cheaper, but it outputs only 480p or 720p and takes fewer reference files.
How long can a Seedance 2.5 Flash video be?
From 4 to 30 seconds, chosen with duration. The reference-to-video endpoint also accepts -1 to let the model pick the length.
Does Seedance 2.5 Flash generate audio?
Yes. Set audio_enable: true. In our tests, clips with audio cost the same as the token formula predicts for the video alone.
Does Seedance 2.5 Flash support image-to-video?
Yes. Use bytedance/seedance-2.5-flash-i2v-spicy with image as the first frame and optional end_image as the last frame. The reference endpoint accepts up to 10 images, 5 videos and 5 audio files.
How long does Seedance 2.5 Flash take to generate a video?
In our tests, 5- to 10-second clips took 72 to 100 seconds from submit to finish, and five tasks submitted at the same time did not slow each other down.
Try Seedance 2.5 Flash Spicy on Siray AI
Get an API key and run your first clip from the Seedance 2.5 Flash t2v Spicy model page. The same key works for the image-to-video and reference-to-video endpoints and for every other model on Siray AI.
Sources
- ByteDance Seed, Seedance 2.5, accessed November 16, 2026.
- BytePlus, Dreamina Seedance 2.5 announcement, accessed November 16, 2026.
- Pandaily, ByteDance Releases Seedance 2.5 Flash, accessed November 16, 2026.
- Siray AI API reference: t2v Spicy, i2v Spicy, ref2v Spicy, accessed November 16, 2026.
- Siray AI pricing API,
GET /v1/models/pricing/{model}, November 16, 2026.