

Seedance 2.5 Flash and Seedance 2.0 Fast side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Seedance 2.5 Flash and Seedance 2.0 Fast are both ByteDance models in the Video Generation category, available through the EmpirioLabs API.
| Spec | Seedance 2.5 Flash | Seedance 2.0 Fast |
|---|---|---|
| Model ID | seedance-2-5-flash | seedance-2-0-fast |
| Author | ByteDance | ByteDance |
| Released | Nov 12, 2026 | Feb 12, 2026 |
| Input | Text Image Video Audio | Text Image Video Audio |
| Output | Video | Video |
| Region | Malaysia | Malaysia |
| Endpoints | POST /v1/videos/generations | POST /v1/videos/generations |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | Seedance 2.5 Flash | Seedance 2.0 Fast |
|---|---|---|
| prompt | string | string |
| resolution | 480p, 720p Default: 720p | 480p, 720p Default: 720p |
| aspect_ratio | adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 Default: adaptive | adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 Default: adaptive |
| custom_duration | boolean Default: true | boolean Default: true |
| duration | 4 to 30 Default: 5 | 4 to 15 Default: 5 |
| generate_audio | boolean Default: true | boolean Default: true |
| output_format | mp4, mov Default: mp4 | - |
| return_last_frame | boolean Default: false | - |
| image | string | string |
| image_end | string | string |
| reference_images | array | - |
| videos | array | - |
| audios | array | - |
| negative_prompt | string | string |
| seed | -1 to 2147483647 | - |
| mode | - | auto, t2v, i2v_first, i2v_both, reference, edit, extend Default: auto |
A faster, lower-cost Seedance 2.5 that keeps most of its creative range: one request can produce a coherent clip of up to 30 seconds at 480p or 720p, draw on up to 20 reference assets, and edit or extend existing footage.
Speed-optimized variant of Seedance 2.0 Pro: faster, lower-cost, ideal for rapid iteration. 480p and 720p only (no 1080p).
Seedance 2.5 Flash runs through POST /v1/videos/generations. The request returns a job_id right away; poll GET /v1/jobs/{job_id} until the job completes and read the output URLs from the result. Both models are called through the same endpoint. Set model to seedance-2-5-flash or seedance-2-0-fast. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/videos/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-5-flash",
"prompt": "Describe what you want Seedance 2.5 Flash to generate."
}'Prompt tests and comparison runs that cover both models.
Seedance 2.5 Flash is the newer release (Nov 12, 2026); Seedance 2.0 Fast was released on Feb 12, 2026. Capabilities listed only for Seedance 2.5 Flash: text to video, image to video, reference to video, video editing, multimodal, character consistency. Seedance 2.0 Fast lists the lower rate for T2V/I2V 480P (per second) and T2V/I2V 720P (per second). The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Seedance 2.5 Flash is the newer release (Nov 12, 2026); Seedance 2.0 Fast was released on Feb 12, 2026.
Seedance 2.0 Fast lists the lower rate for T2V/I2V 480P (per second) and T2V/I2V 720P (per second). Both live rate cards are on this page and always match what the API charges.
Yes. Both models use POST /v1/videos/generations with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.