> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server. # Seedance 2.5 Flash > Faster, lower-cost Seedance 2.5 for coherent clips up to 30 seconds at 480p or 720p, with image, video, and audio references, native audio, editing, and… ![Seedance 2.5 Flash](https://media.empiriolabs.ai/model-logos/seedance-2-5.png) [ByteDance](/providers/bytedance) · Video Generation `POST /v1/videos/generations` Faster, lower-cost Seedance 2.5 for coherent clips up to 30 seconds at 480p or 720p, with image, video, and audio references, native audio, editing, and extension. ## At a glance | Field | Value | | ------------------- | ------------------------------------------------------------------------------------------------------------------------------- | | Model id | `seedance-2-5-flash` | | Model release date | 2026-11-12 | | Input modalities | Text, Image, Video, Audio | | Output modalities | Video | | Context window | - | | Weight precision | - | | Region | Malaysia | | Features | text_to_video, image_to_video, reference_to_video, video_editing, multimodal, audio_sync, camera_control, character_consistency | | Native inference | No | | New | Yes | | Supported endpoints | `POST /v1/videos/generations` | | Alternate model ids | `bytedance/seedance-2.5-flash`, `seedance-2.5-flash` | ## Pricing | Charge | Spec | Rate | | ---------------- | ------------------------------- | ------- | | T2V/I2V 480P | per second | \$0.135 | | T2V/I2V 720P | per second | \$0.302 | | Video Input 480P | per second of input plus output | \$0.083 | | Video Input 720P | per second of input plus output | \$0.186 | ## Example request ```bash 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": "sunrise over the ocean", "duration": 6}' ``` ## Parameters | Parameter | Type | Required | Default | Description | | ------------------- | ------- | -------- | ------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `prompt` | string | yes | - | Scene description. Address a specific attachment inline as @Image1, @Video1, or @Audio1 to say which reference a shot should follow. | | `mode` | enum | no | `"auto"` | Selects how your inputs are used. auto detects it from what you attach. t2v is text to video. i2v_first animates a first frame. i2v_both animates between a first and a last frame. reference builds from up to 10 images, 5 videos and 5 audio clips. To edit or continue an attached clip, say so in the prompt. · Allowed: `auto`, `t2v`, `i2v_first`, `i2v_both`, `reference` | | `resolution` | enum | no | `"720p"` | Output resolution. · Allowed: `480p`, `720p` | | `aspect_ratio` | enum | no | `"adaptive"` | Output aspect ratio. adaptive lets the model choose. With a first frame, the video always follows that image's aspect ratio. Editing an attached video keeps that video's aspect ratio and length. Other reference jobs, including ones with a reference video, accept any ratio. · Allowed: `adaptive`, `16:9`, `9:16`, `1:1`, `4:3`, `3:4`, `21:9` | | `custom_duration` | boolean | no | true | If false, the model decides clip length. | | `duration` | number | no | `5` | Clip length in seconds. Only used when custom_duration=true. Video editing always keeps the source clip length, and the clip being edited must be 4 to 30 seconds long. · Range: 4 – 30 | | `generate_audio` | boolean | no | true | Generate native audio with the video. | | `output_format` | enum | no | `"mp4"` | mp4 plays everywhere. mov carries higher color precision for color grading, keying, and compositing, and some players cannot open it. · Allowed: `mp4`, `mov` | | `return_last_frame` | boolean | no | false | Also return the final frame as a PNG, ready to use as the first frame of the next clip. | | `image` | string | no | - | Reference / first-frame image URL. | | `image_end` | string | no | - | End-frame image URL for i2v_both. | | `video` | string | no | - | Reference video URL for reference / edit / extend. | | `negative_prompt` | string | no | `""` | What to avoid. | | `seed` | number | no | - | Integer seed for reproducible-style output. Same seed gives similar, not identical, results. · Range: -1 – 2147483647 | ## Notes 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. **Modes** * Text to video, first frame, or first and last frame. * Multimodal reference to video from up to 10 images, 5 videos, and 5 audio clips. Audio-only input works on its own. * To edit an attached clip or continue it, describe that in your prompt. The model reads the intent from your wording. **Output** * 480p and 720p at 24fps, 4 to 30 seconds, with native synchronized audio. * MP4 by default. MOV carries higher color precision for grading and compositing, and some players cannot open it. * When you supply a first frame, the output follows that image's aspect ratio, so aspect_ratio stays adaptive. Reference jobs, including ones with a reference video, accept any ratio. **Input limits** * Images: jpeg, png, webp, bmp, tiff, gif, heic, or heif, 300 to 6000 px per side, under 30 MB each. * Videos: MP4 or MOV, 2 to 30 seconds each and 30 seconds in total, under 200 MB each. * Audio: WAV or MP3, 2 to 30 seconds each and 30 seconds in total, under 15 MB each. * Reference uploads that contain real human faces are rejected by the model. To use your own face, email [support@empiriolabs.ai](mailto:support@empiriolabs.ai). **Billing** * Without a reference video, you are billed per second of generated video at the rate for the output resolution. * With a reference video, the model prices the reference clip's seconds alongside the generated seconds, at the lower video-input rate. Billed seconds are therefore reference duration plus output duration, so a request that includes a reference video costs more in total than the same output generated from text alone. * Worked example at 480p: a 4 second clip from a text prompt bills 4 seconds. A 4 second clip generated from a 5 second reference video bills 9 seconds at the video-input rate. **Uploaded media preprocessing** * Video inputs are capped to 30 seconds. * Uploaded video inputs are normalized to provider-compatible MP4 when needed. Set preprocess_video to false to send a clip through untouched. --- *Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/seedance-2-5-flash`.