ByteDanceVideoReleased 7 August 2026

Seedance 2.5 pricing, context and benchmark

Seedance 2.5 is a video generation model from ByteDance.

n/a
Input context
n/a
Output context
$0.1028
Per second
1
Providers
n/a
AA index

Everything that matters, in one table

Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.

ModelSeedance 2.5
Model IDbytedance/seedance-2.5
ProviderByteDance
Release date7 August 2026
StatusGenerally available
Input contextProvider default
Output contextProvider default
Official input pricingFree per 1M tokens
Official output pricingFree per 1M tokens
Cache read pricingNot published
Market input pricingFree per 1M (cheapest route)
Market output pricingFree per 1M (cheapest route)
Input modalitiestext · image · video · audio
Output modalitiesvideo
Reasoning controlNot exposed
Tool supportText generation only
TokenizerMedia
Provider routes1 endpoint
Artificial Analysis indexNot published
SpeedNot published
Knowledge cutoffNot publicly stated

Input and output support

ModalityInputOutputBilled at
Text✓ yesnoFree in
Image✓ yesnoFree in
Audio✓ yesnoFree in
Video✓ yes✓ yesFree in
File (PDF)nononot supported

What is Seedance 2.5?

Seedance 2.5 is a video generation model from ByteDance.

It is suited for long-form storytelling, multimodal reference-based generation, video editing, and video extension.

It supports first-frame and first-and-last-frame control, up...

Seedance 2.5 carries a n/a token window, uses the Media tokenizer and is served by ByteDance. On Hoodgen it sits in the Video tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.

Release and what changed from the previous version

Released7 August 2026
PropertyFLUX 3 VideoSeedance 2.5Change
ReleasedAug 2026Aug 2026Same release window
Contextn/an/aUnchanged
Max outputn/an/aUnchanged
Input priceFreeFreeUnchanged
Output priceFreeFreeUnchanged
Input modalitiestext, image, videotext, image, video, audioUnchanged
AA indexn/an/aNewer benchmark run

Features and capabilities

◉
Vision
Screenshots, charts and photographed documents are read at the text token rate.
♪
Audio and video
Calls, meetings and screen recordings can be summarised in one pass.

What can you do with Seedance 2.5?

Everyday writing
Drafts, rewrites, summaries and replies.
Research
Source material condensed with the key numbers kept.
Chat
General questions where latency and cost both matter.
Tooling inside Hoodgen
Writer, Humanizer, Coding and the rest of the tool suite.

Seedance 2.5 pricing

Official pricing

Per second
$0.1028 / second
  • Video (with audio) (480p): $0.1028 per second
  • Video (no audio) (480p): $0.1028 per second
  • Video (with video input) (480p): $0.0615 per second
  • Video Tokens (with audio): $10.7 per M tokens
  • video output from text, image, video, audio input
Cheapest route
Free / 1M in
Free / 1M out
  • 1 route on OpenRouter
  • What Hoodgen routes to first
  • Same model, lower bill

Market pricing, every route

ProviderTierInputOutputCache readUptime 24h
Seedstandardn/an/an/a100.0%

API pricing and cost calculator

RatePer callTotalCredits
Cheapest route$0.0000$0.001
List price$0.0000$0.001

API and developer information

Model IDbytedance/seedance-2.5
Endpointhttps://openrouter.ai/api/v1/chat/completions
Parametersprompt and max_tokens
StreamingYes, server sent events
Modality stringtext+image+audio+video->video
Max prompt tokensprovider default
Max completion tokensprovider default
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bytedance/seedance-2.5",
    "messages": [{ "role": "user", "content": "Summarise this document." }],
    "max_tokens": 1024
  }'

Model limitations

Output capProvider default tokens per request. Long deliverables have to be chunked.
Benchmarks not publishedArtificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here.
Knowledge cutoffThe provider does not state a fixed cutoff for every release. Verify very recent events against search.

Seedance 2.5 vs other ByteDance models

ModelContextInput /1MOutput /1MAA indexReleased
Seedance 2.5n/aFreeFreen/aAug 2026
Wan 2.7n/aFreeFreen/aApr 2026
FLUX 3 Videon/aFreeFreen/aAug 2026
FLUX Video Editn/aFreeFreen/aSept 2026
FLUX Video Upscalen/aFreeFreen/aAug 2026
Seedance 2.0n/aFreeFreen/aApr 2026

Privacy and data policy

  • On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
  • Requests route through OpenRouter to ByteDance and are covered by that provider's API terms.
  • Do not paste secrets or personal data you would not send to any hosted model.

Seedance 2.5 questions, answered

Seedance 2.5 is a video model from ByteDance, released 7 August 2026. Seedance 2.5 is a video generation model from ByteDance.
✦

Start chatting with Seedance 2.5

Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.