Compare models

Choose two or three models. Copy the URL to share your selection.

Model 1

Model 2

Comparison	Seedance 2.5 `seedance-2.5`	Choose model 2
Type	Video	—
Best for	Videos with sound from text, first/last frames and ordered image, video or audio references	—
TokenRex price	$0.072 per second (480p)	—
Cached input / 1M tokens	No separate cached rate listed	—
Cache write / 1M tokens	Not applicable	—
Cached output	Not offered · standard output rate applies	—
Web search	Not applicable	—
Market price	$0.103 per second (480p)	—
Input token limit (provider)	Within the context window	—
Vendor input modalities	Text, Image, Video, Audio	—
Vendor output modalities	Video with audio	—
TokenRex endpoints	POST /v1/videos · GET /v1/videos/{id}	—
TokenRex input	Prompt up to 25,000 characters (optional with references), First frame and optional last frame, Up to 30 ordered reference images, Up to 10 reference videos (public HTTPS, 30 s combined), Up to 10 reference audio clips (30 s combined)	—
TokenRex output	Asynchronous video job; poll, then download the MP4	—
Duration accepted by TokenRex	4–30 seconds, or Auto (-1)	—
Resolution accepted by TokenRex	480p or 720p	—
Aspect ratios	16:9, 4:3, 1:1, 3:4, 9:16, 21:9 or adaptive	—
Frame rate and format	24 fps MP4 only	—
Sound	generate_audio on or off	—
Benchmarks
Benchmark evidence	2 source-linked results	—
AA-Video-T2V v2.1	1155Elo Listed as Dreamina Seedance 2.5. Pairwise blind human-preference Elo, ±13 (95% interval 1142–1168), 7,765 votes; 4th overall when checked. Not a TokenRex run. Artificial Analysis · Text-to-Video Arena	—
AA-Video-I2V v2.1	1161Elo Listed as Dreamina Seedance 2.5. Pairwise blind human-preference Elo, ±15 (95% interval 1146–1176), 6,540 votes; 1st overall when checked. Not a TokenRex run. Artificial Analysis · Image-to-Video Arena	—

No overall score, winner or cost-versus-score frontier is calculated without comparable, attributable benchmark evidence. Different test configurations appear separately. Vendor capabilities are distinct from TokenRex API support.

— means no published value or no matching capability. Provider token limits are not tested gateway guarantees; TokenRex media controls and response formats are listed separately.

Seedance 2.5

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

TokenRex video and image API documentation
Vendor-reported
Last checked 2026-11-11
Cloudflare Workers AI: ByteDance Seedance 2.5
Vendor-reported
Last checked 2026-11-11
OpenRouter: ByteDance Seedance 2.5
Third-party report
Last checked 2026-11-11
Lovable AI video documentation
Vendor-reported
Last checked 2026-11-11

Research notes (4)

Functional test through TokenRex (2026-11-11): a 4-second 480p job with sound and one reference image completed in about 2 minutes and downloaded as an 854×480, 24 fps MP4 with AAC audio. This is a working check, not a quality benchmark.
A request whose generated sound resembled copyrighted music was refused by the provider's safety check; refused jobs are not charged.
720p, reference-video and reference-audio requests are accepted by validation but were not rendered in TokenRex's own tests.
camera_fixed is accepted but has no observed effect. use_virtual_avatar is a provider policy option and does not bypass real-person or deepfake restrictions.

Popular comparisons

Open the cost calculator →