Models & pricing / Seedance 2.5 Flash · Volcengine
By ByteDance · Provider Volcengine

Seedance 2.5 Flash API · Volcengine

Seedance 2.5 Flash is a ByteDance video model using text and image, video or audio references. Volcengine offers 480p and 720p output. Compare delivery requirements, reference limits and current XiuAI rates when planning multiple generations.[2][5]

doubao-seedance-2-5-flash-261115

Model overview

Published provider specifications. Available features depend on the current API route.

Input
Text, image URLs, video URLs and audio URLs
Output
Video with optional synchronized audio
Duration
4–30 seconds
Resolution
480p / 720p
Reference limits
10 images · 5 videos · 5 audio clips
Frame rate
24 fps
API routes
Ark API / Unified video API

Where Flash fits

When exploring a creative direction, keep inputs, resolution and duration consistent while changing one aspect of the action, camera or scene. Use first-frame mode for an existing product image or composition. Once you choose a direction, decide whether you need the higher output specifications offered by 2.5.[2]

Flash also supports reference-guided requests, editing and extension within its own limits. Your application prepares assets, organizes tasks, reviews outputs and stores results. Review references and prompts; the Flash name does not establish a fixed speed or equivalent quality to another model.[2][6]

When to choose Flash

Check whether 480p / 720p meets delivery requirements and whether limits of 10 images, 5 videos and 5 audio clips are sufficient. Compare Seedance 2.5 when you need 1080p or more references.[2]

Once specifications fit, compare current prices and results with matching inputs, resolution and duration. One published example cannot represent every attempt, and processing time needs to be evaluated with your own requests.[5][3]

Input modes and key parameters

Text-to-video, first-frame, first/last-frame and multimodal reference generation use different input roles. Choose the mode before assigning roles in content. Do not mix first/last-frame roles with multimodal reference roles. URLs must remain accessible while the task is processed; reference counts do not replace format, size or combined-duration requirements.[2]

Use ratio=adaptive for first-frame, first/last-frame, editing and extension tasks. Editing also requires duration=-1 so output follows the reference clip. Duration describes clip length, not processing time. Audio references and generate_audio are separate choices; check both before submission.[2]

Understanding generation costs

Charges depend on video-token usage and the applicable rate. Resolution, actual output and reference video affect usage; video inputs can also have minimum billable usage. A lower reference-video rate does not necessarily produce a lower total charge. Compare input conditions, specifications and usage together.[3]

Prices and published examples on this page come from the current catalog. Each example has stated specifications and usage assumptions; it is not a quote for your request or a universal per-second rate. Each deliberate new generation is billed separately. Reconcile recorded charges using task and request records.[5][3]

API access

Using the model through XiuAI

Reuse your XiuAI account, balance and an authorized API key. Choose an available protocol listed on this page and copy its matching example with the exact model ID. Ark and unified video API fields differ. Supply accessible reference URLs and save the generated results to your own storage.[5][6]

Save the task ID returned on creation and query that task until it finishes. Continue from task records after leaving the playground, then reconcile charges in request records. If acceptance is unclear, check existing tasks before creating another one. A temporary query error does not establish generation failure.[4][6]

Replace the example first-frame URL with an accessible URL. Query the returned task ID for the result.

POST /api/v3/contents/generations/tasks
curl 'https://router-api.xiu.ai/api/v3/contents/generations/tasks' \
  -H "Authorization: Bearer $XIUAI_API_KEY" \
  -H 'Content-Type: application/json' \
  --data-raw '{
  "model": "doubao-seedance-2-5-flash-261115",
  "content": [
    {
      "type": "text",
      "text": "Slowly push the camera toward a product on a desk, keeping its packaging text sharp."
    },
    {
      "type": "image_url",
      "image_url": {
        "url": "https://assets.example.com/product.jpg"
      },
      "role": "first_frame"
    }
  ],
  "resolution": "720p",
  "duration": 5,
  "ratio": "adaptive",
  "generate_audio": true
}'

Query the task

curl https://router-api.xiu.ai/api/v3/contents/generations/tasks/$TASK_ID \
  -H "Authorization: Bearer $XIUAI_API_KEY"
Read the API documentationView task and charge records

Tasks and data handling

Asynchronous result
Query by task ID after submission. Closing the page does not cancel generation.
Result download
Use the expiry returned with the task and save the result to your own storage before it expires.
Input data
Use accessible URLs you manage. XiuAI does not host input assets or manage creative workflows.

Frequently asked questions

What matters most when comparing Flash with 2.5?

Start with resolution and reference counts, then compare rates under matching conditions and results from your own inputs. Flash offers 480p / 720p, while 2.5 offers 480p / 720p / 1080p. Review input parameters when switching models rather than replacing only the model ID.[2][5]

Is Flash limited to very short clips?

Regular tasks have a provider duration range of 4–30 seconds, with automatic duration where the mode supports it. This describes output length, not the time needed to complete a request.[2]

Are audio references and generated sound the same setting?

No. Audio references guide the task, while generate_audio controls whether audio generation is requested. Check reference roles and output settings separately; supplying audio does not mean output sound is enabled.[2]

Can I keep the same parameters when switching from 2.5 to Flash?

Review them first. Flash offers 480p and 720p output and has its own reference limits. Resolution, reference roles and counts must fit the new model; not every 2.5 setting carries over.[2]

Why can my task cost differ from a published example?

Prices and published examples on this page come from the current catalog. Each example has stated specifications and usage assumptions; it is not a quote for your request or a universal per-second rate. Each deliberate new generation is billed separately. Reconcile recorded charges using task and request records.[5][3]

Can I upload an image or video from my computer?

The current playground accepts accessible HTTPS URLs. Prepare references in your own storage and keep them readable while the task is processed. XiuAI does not provide asset uploads or hosting.[6]

How do I check the cost of this generation in XiuAI?

Find the generation by task ID in Usage to see its current recorded amount, then check associated charges in request records. Creation confirms acceptance; review the result and charge records once the task completes.[4][6]

What should I do if submission or querying is interrupted?

Save the task ID returned on creation and query that task until it finishes. Continue from task records after leaving the playground, then reconcile charges in request records. If acceptance is unclear, check existing tasks before creating another one. A temporary query error does not establish generation failure.[4][6]

Related models

Seedance 2.5 · Volcengine

Sources and updates

Specifications reference provider documentation; prices and availability come from the current XiuAI catalog. Specifications checked: 2026-11-15

Content reviewed: 2026-11-16

[1] ByteDance model introduction[2] Volcengine request parameters[3] Volcengine billing guide[4] Volcengine task retrieval[5] Current XiuAI model and pricing data[6] XiuAI Data Privacy