Seedance 2.0
Strong realism, 9 images and 3 clips — also edits clips. By ByteDance.
bytedance/seedance-2.0/image-to-video
const res = await fetch("https://api.elyum.ai/v1/generations", { method: "POST", headers: { Authorization: `Bearer ${process.env.ELYUM_API_KEY}`, "Content-Type": "application/json", Prefer: "wait=55", }, body: JSON.stringify({ "model": "bytedance/seedance-2.0/image-to-video", "prompt": "A slow push-in on a lighthouse at dusk, waves breaking below", "inputs": [ { "role": "first_frame", "url": "https://example.com/reference.jpg" } ] }),});const generation = await res.json();console.log(generation.status, generation.outputs);Result
$0.0653 at 480p, $0.1404 at 720p, $0.3507 at 1080p and $0.7139 at 4K per second of video. Charged when the file is delivered; a render that fails or is canceled costs nothing.
Seedance 2.0 image to video uses the model id bytedance/seedance-2.0/image-to-video. Strong realism, 9 images and 3 clips — also edits clips
1. Calling the API
Endpoint
Send a POST to https://api.elyum.ai/v1/generations with a JSON body matching the parameters below. Every model uses the same endpoint; the model field picks this one.
const res = await fetch("https://api.elyum.ai/v1/generations", { method: "POST", headers: { Authorization: `Bearer ${process.env.ELYUM_API_KEY}`, "Content-Type": "application/json", Prefer: "wait=55", }, body: JSON.stringify({ "model": "bytedance/seedance-2.0/image-to-video", "prompt": "A slow push-in on a lighthouse at dusk, waves breaking below", "inputs": [ { "role": "first_frame", "url": "https://example.com/reference.jpg" } ] }),});const generation = await res.json();console.log(generation.status, generation.outputs);Request parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Yes | — | bytedance/seedance-2.0/image-to-video, or bytedance/seedance-2.0 to let your inputs pick the task. |
prompt | string | Yes | — | Sent to the model as written, never shortened. |
inputs | array | Yes | — | Files the task takes, each with a role and a url or file. See Inputs. |
duration | number | No | 5 | 4 to 15, whole numbers |
resolution | string | No | "720p" | 480p, 720p, 1080p, 4k |
aspect_ratio | string | No | — | 9:16, 1:1, 16:9, 4:3, auto |
audio | boolean | No | true | true or false |
max_usd | number | No | — | Refuse the render, with nothing held, if it would cost more than this many dollars. |
metadata | object | No | — | Up to 16 string pairs, echoed back on the generation. |
A value outside these lists is refused with a 400 naming the field, before anything is charged. Nothing is quietly rounded or dropped.
Inputs
| Role | Types | Required | Limits |
|---|---|---|---|
first_frame | image | Yes | — |
Cite an input in the prompt by type and order (@image1, @video1, @audio1), or give it a name and cite @name. An input outside these limits is refused with a 400 naming it, before anything is charged.
2. Authentication
API key
Create a key on Keys with the generate and spend scopes and send it as a bearer token. Keep it on your server; never send it to a browser.
Authorization: Bearer $ELYUM_API_KEY3. Queue
Submit and wait
With Prefer: wait=55 the request holds until the render ends or 55 seconds pass. A finished render answers 200 with its outputs; one still running answers 202 with its id.
Poll and cancel
const headers = { Authorization: `Bearer ${process.env.ELYUM_API_KEY}` }; // Poll until the render ends: succeeded, failed or canceledlet generation = await (await fetch(`https://api.elyum.ai/v1/generations/${id}`, { headers })).json();while (generation.status === "queued" || generation.status === "running") { await new Promise((r) => setTimeout(r, 5000)); generation = await (await fetch(`https://api.elyum.ai/v1/generations/${id}`, { headers })).json();} // Or stop it (a hold is refunded)await fetch(`https://api.elyum.ai/v1/generations/${id}/cancel`, { method: "POST", headers });Output links are signed and last 24 hours: download them to your own storage, or fetch the generation again for fresh ones.
4. Pricing
| Resolution | Price |
|---|---|
| 480p | |
| 720p | |
| 1080p | |
| 4K |
A struck price is the list price before today's. Send ?dry_run=true for the exact price of a request with nothing held. The API spends your API balance; a render that fails or is canceled costs nothing.
Compare with others
What every provider charges for Seedance 2.0, from their own pricing pages. The line under our price is how much less you pay.
| Resolution | Elyum | Higgsfield | fal.ai | Kie.ai | Sume | Sunra |
|---|---|---|---|---|---|---|
| 480p | $0.0653 / s−54 % vs Higgsfield · −1.1 % vs Sunra | $0.1407 / s | $0.1406 / s | $0.095 / s | $0.0711 / s | $0.066 / s |
| 720p | $0.1404 / s−54 % vs fal.ai · −1.1 % vs Sunra | $0.3024 / s | $0.3034 / s | $0.205 / s | $0.1538 / s | $0.1419 / s |
| 1080p | $0.3507 / s−49 % vs fal.ai · −1 % vs Sunra | $0.6804 / s | $0.682 / s | $0.51 / s | $0.3846 / s | $0.3543 / s |
| 4K | $0.7139 / s−54 % vs Higgsfield · −1 % vs Sunra | $1.5552 / s | $1.5552 / s | $1.04 / s | — | $0.7212 / s |
| 480p, with a reference clip | $0.0397 / s−53 % vs Higgsfield · −1.2 % vs Sunra | $0.0844 / s | — | $0.057 / s | $0.0711 / s | $0.0402 / s |
| 720p, with a reference clip | $0.0855 / s−53 % vs Higgsfield · −1 % vs Sunra | $0.1814 / s | — | $0.125 / s | $0.1538 / s | $0.0864 / s |
| 1080p, with a reference clip | $0.2131 / s−48 % vs Higgsfield · −1 % vs Sunra | $0.4082 / s | — | $0.31 / s | $0.3846 / s | $0.2153 / s |
| 4K, with a reference clip | $0.4407 / s−53 % vs Higgsfield · −1 % vs Sunra | $0.9331 / s | — | $0.64 / s | — | $0.4452 / s |
The most expensive provider is in red; * is a limited-time promotion, counted while it runs. A dash means the provider does not sell it. A row with a reference clip is priced per second of the clip and the output together, against the providers that bill a clip's seconds that way; the clip's seconds are always charged. Prices read from each provider's pricing page on 2026-10-27; every model and source.
More models by ByteDance
Seedance 2.0 task by task, then the lowest price of each other model. What a render costs depends on the resolution and length you choose.
| Model | Price | Resolution | Length |
|---|---|---|---|
| Seedance 2.0 Text to video | $0.0653 – $0.7139 / s | 480p – 4K | 4 – 15 s |
| Seedance 2.0 Image to video | $0.0653 – $0.7139 / s | 480p – 4K | 4 – 15 s |
| Seedance 2.0 Reference to video | $0.0653 – $0.7139 / sWith a reference clip: $0.0397 – $0.4407 / s of clip + output | 480p – 4K | 4 – 15 s |
| Seedance 2.0 Video edit | $0.0397 – $0.4407 / s of clip + output | 480p – 4K | — |
| Seedance 2.5Text to video · Image to video · Reference to video · Video edit | from $0.1016 / s | 480p – 1080p | 4 – 30 s |
| Seedance 2.0 FastText to video · Image to video · Reference to video · Video edit | from $0.09 / s | 480p – 720p | 4 – 15 s |
| Seedance 2.0 MiniText to video · Image to video · Reference to video · Video edit | from $0.09 / s | 480p – 720p | 4 – 10 s |
| Seedream 5 ProText to image · Image edit | $0.07 / image | — | — |
| Seedream 5 LiteText to image · Image edit | $0.04 / image | — | — |
| Seedream 4.5Text to image · Image edit | $0.04 / image | — | — |
| SeedVR2Image upscale · Video upscale | $0.05 / render | — | — |