中文 AI 视频模型对比

最长单段

15 秒

最高分辨率

4K resolution enum 720p | 1080p | 4k; 4K bills at $0.42/s against $0.084/s at 720p

帧率

厂商未公布 Kling publishes no frame rate — its own Video Capability Map lists duration and resolution and no fps, and no endpoint takes an fps parameter

原生音频

有 opt-in: settings.audio enum native | off, default off

生成模式

T2V · I2V · FL2V · REF2V ref2v runs through the Element library rather than raw reference images

价格（国际站）

$0.084 / 秒 720p without native audio. 1080p $0.112/s, 4K $0.42/s; with native audio 720p $0.126/s, 1080p $0.168/s. Billed in Units, 1 Unit = $0.14

开放 API

有

最短单段

3 秒

水印

optional options.watermark_info.enabled defaults false; when true a watermarked copy is returned alongside the clean one

可用区域

global, single Singapore API endpoint api-singapore.klingai.com is the only regional endpoint documented on the international open platform

反向提示词

无 the current endpoint has no negative_prompt field — positive and negative descriptions both go in the prompt. The superseded legacy endpoint did expose one

最多输入图片

2 first_frame + last_frame; last-frame-only is not supported. Up to 3 Elements may additionally be referenced

目录条目: Kling

最长单段

15 秒

最高分辨率

4K

原生音频

有 settings.audio enum native | off, default off

生成模式

T2V · I2V · FL2V · REF2V · V2V video reference and multi-image to video are marked supported on Omni and O1 only

价格（国际站）

$0.084 / 秒 720p, no video input, no native audio. With native audio 720p $0.112/s, 1080p $0.14/s; with video input 720p $0.126/s, 1080p $0.168/s; 4K $0.42/s throughout

开放 API

有

最短单段

3 秒

水印

optional

反向提示词

无

目录条目: Kling

最长单段

15 秒

最高分辨率

1080p enum is 720p | 1080p only — no 4K on Turbo, unlike Kling 3.0

原生音频

有 always on — the endpoint exposes no audio toggle and the price list carries only a 'with native audio' row

生成模式

T2V · I2V the capability map shows no first/last frame and no Element control for Turbo

价格（国际站）

$0.112 / 秒 720p with native audio (0.8 Units/s); 1080p $0.14/s

开放 API

有

最短单段

3 秒

水印

optional

反向提示词

无

目录条目: Kling

最长单段

10 秒

最高分辨率

1080p

原生音频

无 the audio enum is original | off — 'original' RETAINS an input video's sound; the model synthesises none, and the price list has no audio dimension for O1

生成模式

T2V · I2V · FL2V · REF2V · V2V content types: prompt, first_frame, last_frame, refer_image, feature_video, base_video, element

价格（国际站）

$0.084 / 秒 720p, no video input; 1080p $0.112/s. With video input 720p $0.126/s, 1080p $0.168/s

开放 API

有

最短单段

3 秒 integers 3-10; with only a first frame and no other reference, only 5 or 10 are accepted

水印

optional

反向提示词

无

目录条目: Kling

最长单段

10 秒

可选时长

5 / 10 秒 the API duration enum is exactly {5, 10} on both t2v and i2v. Kling's own Video Capability Map advertises 3~10s for this model; that range is NOT reachable through the documented API

最高分辨率

1080p

原生音频

有 audio=native FORCES 1080p — no 720p rate exists for the audio tiers

生成模式

T2V · I2V · FL2V · S2V s2v is voice-reference input (at most 2 voices) and requires audio != off; first+last frame requires 1080p

价格（国际站）

$0.042 / 秒 720p silent; 1080p silent $0.07/s; with native audio (1080p only) $0.14/s; with voice control $0.168/s

开放 API

有

水印

optional

反向提示词

无

目录条目: Kling

最长单段

10 秒

可选时长

5 / 10 秒

最高分辨率

1080p

原生音频

无 no audio parameter on this endpoint; the price list carries only a 'no native audio' row

生成模式

T2V · I2V · FL2V

价格（国际站）

$0.042 / 秒 720p; 1080p $0.07/s

开放 API

有

水印

optional

目录条目: Kling

最长单段

30 秒 duration accepts [4, 30] or -1 for smart duration (the default). Video-EDITING tasks accept only -1 — you cannot specify an output length there

最高分辨率

1080p 480p | 720p | 1080p, default 720p. NO 4K on 2.5 — only Seedance 2.0 offers it, so 'Seedance: up to 4K' is wrong for the current flagship. 1080p output is 10-bit H.265, which some players cannot decode

帧率

24 fps

原生音频

有 generate_audio defaults to TRUE; output audio is always mono regardless of input channels

生成模式

T2V · I2V · FL2V · REF2V · V2V · S2V omni reference takes 0-30 images, 0-10 videos and 0-10 audio clips; 2.5 is the only version accepting audio-ONLY input

价格（国际站）

$0.231 / 秒 vendor's own worked example: 720p 16:9 5s with no video input. 480p $0.103/s, 1080p $0.569/s. Billing is per TOKEN underneath, so reference video raises the bill sharply — 1080p with 30s of input video reaches $11.907 for a 5s output

开放 API

有 gated: needs an account balance over USD 30, a USD 30+ AI Savings Plan, or a purchased Seedance resource pack

最短单段

4 秒

水印

optional watermark boolean defaults FALSE; true stamps 'AI Generated' bottom-right. This is the BytePlus international endpoint — mainland AIGC labelling obligations attach to the Volcano Engine service instead

可用区域

ap-southeast-1 only base URL ark.ap-southeast.bytepluses.com. Volcano Engine 火山引擎 is the separate mainland-China console for the same models, with different model IDs, pricing and labelling duties

反向提示词

无 no negative-prompt parameter anywhere in the request body; steering is positive-only

最多输入图片

30 omni reference accepts 1-30. First-frame i2v takes 1 and first+last takes 2, and those modes are MUTUALLY EXCLUSIVE with omni reference

发布 2026-06-28

目录条目: Seedance

最长单段

15 秒 [4, 15] or -1

最高分辨率

4K 480p | 720p | 1080p | 4k — the ONLY Seedance version offering 4k, and it is rate-limited far harder (15 RPM, concurrency 1) and encoded 10-bit H.265

帧率

24 fps

原生音频

有

生成模式

T2V · I2V · FL2V · REF2V · V2V omni reference takes 0-9 images, 0-3 videos, 0-3 audio; audio-only input is NOT supported, unlike 2.5

价格（国际站）

$0.15 / 秒 720p 16:9 5s, no video input. 480p $0.07/s, 1080p $0.37/s, 4K $0.78/s

开放 API

有

最短单段

4 秒

水印

optional

可用区域

ap-southeast-1 only

反向提示词

无

最多输入图片

9

发布 2026-01-28

目录条目: Seedance

最长单段

15 秒

最高分辨率

720p 480p | 720p only — no 1080p and no 4k

帧率

24 fps

原生音频

有

生成模式

T2V · I2V · FL2V · REF2V · V2V

价格（国际站）

$0.12 / 秒 720p 16:9 5s, no video input; 480p $0.06/s. A limited-time 25% discount ran 7 Aug - 7 Sep 2026

最短单段

4 秒

最多输入图片

9

发布 2026-01-28

目录条目: Seedance

最长单段

15 秒

最高分辨率

720p 480p | 720p only

帧率

24 fps

原生音频

有

生成模式

T2V · I2V · FL2V · REF2V · V2V

价格（国际站）

$0.08 / 秒 720p 16:9 5s, no video input; 480p $0.04/s. Cheapest Seedance tier; a 60% discount ran 7 Aug - 7 Sep 2026

最短单段

4 秒

发布 2026-06-15

目录条目: Seedance

最长单段

12 秒 [4, 12] or -1

最高分辨率

1080p 480p | 720p | 1080p, default 720p

帧率

24 fps

原生音频

有

生成模式

T2V · I2V · FL2V no reference-to-video and no video input — those arrived with 2.0. Uniquely supports a cheap draft mode, re-run from the draft's task ID

开放 API

有 the only Seedance version also offered on the cheaper flex offline-inference tier

最短单段

4 秒

最多输入图片

2 first_frame + last_frame

发布 2025-12-15

目录条目: Seedance

最长单段

12 秒 [2, 12] — the only versions reaching down to 2s

最高分辨率

1080p 480p | 720p | 1080p, and uniquely DEFAULTS to 1080p rather than 720p

帧率

24 fps

原生音频

无 generate_audio is supported only on 2.5, the 2.0 series and 1.5 Pro — the 1.0 models are silent-only

生成模式

T2V · I2V · FL2V 1.0 Pro Fast drops first+last frame — text-to-video and first-frame image-to-video only

最短单段

2 秒

发布 2025-05-28

目录条目: Seedance

最长单段

30 秒 the app's standard mode, matching the API's single-generation cap. The page also advertises extension to 180 seconds in a beta long-video mode, which is stitching rather than one continuous generation

最高分辨率

厂商未公布 unresolved between two vendor pages: the Dreamina product page claims 4K, while the ModelArk API caps dreamina-seedance-2-5 at 1080p and exposes 4k only on Seedance 2.0. Both are ByteDance's own surfaces, so the conflict IS the finding — recorded as unknown rather than picking a side

原生音频

有

生成模式

T2V · I2V · REF2V · S2V the app accepts text prompts, scripts, reference photos, videos, music and style guides, plus a green-screen reference workflow

开放 API

无 Dreamina is a credit-billed consumer app and publishes no API of its own. The same models are exposed programmatically through BytePlus ModelArk — see the `seedance` entry

水印

free-tier watermark-free download is a paid upgrade

可用区域

global Dreamina is the international front door; 即梦 at jimeng.jianying.com is the mainland-China one, with separate accounts

目录条目: Jimeng AI 即梦 (Dreamina)

最高分辨率

4K unlike the 2.5 claim, this one IS corroborated by the API, where dreamina-seedance-2-0 accepts resolution=4k

原生音频

有 synchronises narration, dialogue, sound effects and visuals

生成模式

T2V · I2V · REF2V · S2V

开放 API

无

水印

free-tier

最多输入图片

9 up to 12 reference resources — 9 photos, 3 videos, 3 audio clips — exactly matching the ModelArk limits for the 2.0 series

目录条目: Jimeng AI 即梦 (Dreamina)

最长单段

厂商未公布 the Jimeng and Dreamina generator UIs are behind a login wall and neither product publishes a specification page or help-centre article with the in-app duration picker; the model-level limits live on the `seedance` entry instead

生成模式

T2V · I2V · REF2V · S2V the widget labels the mode 全能参考; 数字人 and 动作模仿 are separate tools

开放 API

无 consumer app; the mainland programmatic route is Volcano Engine 火山引擎, a separate product

可用区域

CN mainland

最多输入图片

9 the generator widget states 上传最多12个参考素材 across 图/文/音/视频 — the same 12-slot budget Dreamina breaks down as 9 photos, 3 videos, 3 audio

目录条目: Jimeng AI 即梦 (Dreamina)

最长单段

15 秒

最高分辨率

2K directly selectable on the base create endpoint (resolution enum = 768P | 2K); a SEPARATE regeneration endpoint also upsells 768P→2K at its own price, but 2K is NOT gated behind it

帧率

24 fps

原生音频

有 32 kHz stereo, jointly generated with the video

生成模式

T2V · I2V · FL2V · REF2V · REF2VA one create endpoint; mode is selected by content[].role (first_frame, last_frame, reference_image, reference_video, reference_audio). i2v/fl2v and ref2v are mutually exclusive in one request. Vendor names its two open checkpoints FL2VA and Ref2VA — the trailing 'A' means the output carries audio, so ref2va is the vendor's own framing of reference-to-video+audio

价格（国际站）

$0.13 / 秒 international platform (platform.minimax.io), 2K output. 768P output is $0.08/second. Mainland platform (platform.minimaxi.com) bills ¥0.80/s (2K) and ¥0.50/s (768P). Input material billed separately: first 5 reference images free then $0.04 each; reference video billed at output rate by its own duration; reference audio free. A separate /video-generation-v2-regeneration ENDPOINT re-emits an existing 768P H3 clip at 2K for $0.05/s (mainland CNY 0.30/s); it reuses the MiniMax-H3 model id, so it is an additional route and a billing row rather than a distinct model — and 2K is NOT gated behind it

价格（国内站）

¥0.8 / 秒 mainland platform platform.minimaxi.com, 2K output; 768P is CNY 0.50/s. The regeneration route is CNY 0.30/s. Recorded as a separate field rather than a converted figure: these are two independently-set price lists, not one price in two currencies

开放 API

有

开源权重

有 open-sourced 2026-08-03, after the 2026-07-31 hosted launch; two checkpoints published (MiniMax-H3-Base-FL2VA, MiniMax-H3-Base-Ref2VA)

最短单段

4 秒

许可协议

MiniMax H3 Community License Agreement users in the USA, EU, UK and South Korea must submit an application form before use

水印

optional API: aigc_watermark boolean, optional, DEFAULT false — so API output is unwatermarked unless requested. Documented on the mainland create endpoint and on the international regeneration endpoint, but NOT listed on the international create endpoint. The consumer product (hailuoai.video) is separate and watermarks free-tier downloads

可用区域

global two separate self-serve platforms with different billing currencies: platform.minimax.io (international, USD) and platform.minimaxi.com (mainland China, CNY). Open weights carry a licence application requirement for USA/EU/UK/South Korea

反向提示词

无

最多输入图片

9 reference mode: ≤9 images, ≤3 video clips, ≤3 audio clips, ≤12 files total; per-asset caps video ≤50 MB, image ≤30 MB, audio ≤15 MB, request body ≤64 MB

发布 2026-07-31

目录条目: Hailuo Video 海螺视频

最长单段

10 秒 768P only

可选时长

6 / 10 秒 10s is 768P-only; 1080P is 6s-only

最高分辨率

1080P 6-second clips only; 10-second clips top out at 768P (the default)

帧率

厂商未公布 vendor does not publish an output frame rate for the 2.x line on either the t2v or i2v reference page

原生音频

厂商未公布 vendor documents no audio output for this line — the request schema has no audio field and the response is video only — but it is nowhere stated as absent, so recorded as unpublished rather than false

生成模式

T2V · I2V

价格（国际站）

$0.28 / 条 international platform, 768P 6s. Also 768P 10s $0.56, 1080P 6s $0.49. Mainland: ¥2.00 / ¥4.00 / ¥3.50 per video respectively. Billed PER CLIP, not per second — unlike H3

价格（国内站）

¥2 / 条 mainland platform, 768P 6s; 768P 10s CNY 4.00, 1080P 6s CNY 3.50. Recorded as a separate field rather than a converted figure: these are two independently-set price lists, not one price in two currencies

开放 API

有

开源权重

无

最短单段

6 秒

反向提示词

无

发布 2025-10-28

目录条目: Hailuo Video 海螺视频

可选时长

6 / 10 秒 10s is 768P-only; 1080P is 6s-only

最高分辨率

1080P 6-second clips only

生成模式

I2V listed in the i2v model enum only — it is absent from the t2v model enum, so this variant appears to be image-to-video only

价格（国际站）

$0.19 / 条 international platform, 768P 6s. Also 768P 10s $0.32, 1080P 6s $0.33. Mainland: ¥1.35 / ¥2.25 / ¥2.31 per video

价格（国内站）

¥1.35 / 条 mainland platform, 768P 6s; 768P 10s CNY 2.25, 1080P 6s CNY 2.31. Recorded as a separate field rather than a converted figure: these are two independently-set price lists, not one price in two currencies

开放 API

有

反向提示词

无

目录条目: Hailuo Video 海螺视频

最长单段

10 秒

可选时长

6 / 10 秒 10s available at 512P and 768P; 1080P is 6s-only

最高分辨率

1080P 6-second clips only; this line uniquely also offers 512P

生成模式

T2V · I2V

价格（国际站）

$0.1 / 条 international platform, 512P 6s (cheapest tier). Also 512P 10s $0.15, 768P 6s $0.28, 768P 10s $0.56, 1080P 6s $0.49. Mainland: ¥0.60 / ¥1.00 / ¥2.00 / ¥4.00 / ¥3.50 per video

价格（国内站）

¥0.6 / 条 mainland platform, 512P 6s; 512P 10s CNY 1.00, 768P 6s CNY 2.00, 768P 10s CNY 4.00, 1080P 6s CNY 3.50. Recorded as a separate field rather than a converted figure: these are two independently-set price lists, not one price in two currencies

开放 API

有

开源权重

无

最短单段

6 秒

反向提示词

无

发布 2025-06-18

目录条目: Hailuo Video 海螺视频

最长单段

6 秒

可选时长

6 秒 6 seconds only; 10s not supported on this line

最高分辨率

720P default and only value for this line

生成模式

T2V · I2V · REF2V split across three model IDs and endpoints: T2V-01/-Director (t2v), I2V-01/-Director/-live (i2v), S2V-01 (subject reference, character face only)

开放 API

有 still present in the model enums on the t2v/i2v/s2v reference pages, but ABSENT from the Pay-as-you-go price list entirely — no published price on either platform

开源权重

无

反向提示词

无

最多输入图片

1 S2V-01 only: subject_reference takes a single image (type 'character'); JPG/JPEG/PNG/WebP, <20 MB, shorter side >300px, aspect ratio 2:5 to 5:2

目录条目: Hailuo Video 海螺视频

最长单段

16 秒

最高分辨率

1080p 540p | 720p | 1080p, default 720p

帧率

24 fps

原生音频

有 audio boolean, Q3 only, defaults TRUE (dialogue plus sound effects). bgm is unavailable on Q3

生成模式

T2V · I2V · FL2V

价格（国际站）

$0.12 / 秒 1080p PEAK rate (24 credits/s at $0.005/credit); 720p $0.10/s, 540p $0.045/s. Off-peak roughly halves each — Vidu publishes separate peak and off-peak rates, so any single figure needs the qualifier

开放 API

有

最短单段

1 秒 free-form integer 1-16, default 5

反向提示词

无 documented parameters are prompt, duration, resolution, aspect_ratio, movement_amplitude, style, bgm, audio, seed

最多输入图片

1 image-to-video accepts exactly 1 image; first/last-frame mode takes 2

目录条目: Vidu 维度AI

最长单段

16 秒

最高分辨率

1080p

帧率

24 fps

原生音频

有 audio defaults to TRUE on the Q3 series and emits dialogue plus sound effects; bgm is unavailable on q3. Two qualifiers the earlier scope had wrong: voice_id is documented as "not effective" on the Q3 series, and audio_type is accepted but its SPLITTING is documented as supporting "q2, q1, and 2.0 series models" only — so on Q3 Turbo you get combined audio and cannot isolate speech or effects. Both caveats are stated on image-to-video; the Subjects-Reference to Video body carries audio_type without them.

生成模式

T2V · I2V · FL2V · REF2V

价格（国际站）

$0.065 / 秒 1080p peak (13 credits/s); 720p $0.055/s, 540p $0.035/s; off-peak roughly halves

开放 API

有

最短单段

1 秒 1-16 on t2v/i2v; the reference-to-video endpoint narrows this model to 3-16

反向提示词

无

最多输入图片

7 reference-to-video accepts 1-7; the image-to-video endpoint accepts exactly 1

目录条目: Vidu 维度AI

最长单段

16 秒

最高分辨率

1080p 720p | 1080p only — unlike Q3 Pro and Turbo, this model offers no 540p

帧率

24 fps

原生音频

有 The model emits synchronised audio — the endpoint's own model list describes viduq3-mix as supporting "simultaneous audio and video output" — but NOTHING PARAMETERISES IT. reference-to-video.md documents two endpoints: Subjects-Reference to Video carries audio and audio_type but its model enum excludes viduq3-mix, while Reference to Video accepts viduq3-mix and carries no audio field at all (only bgm, which q3 does not support). So on this model audio cannot be switched off, split, or voiced through the API.

生成模式

REF2V Reference-to-video is the only mode this model accepts. The first/last-frame endpoint (start-end-to-video) does not list viduq3-mix among its accepted models, and pricing carries only reference2video rows for Q3-mix.

开放 API

有

最短单段

1 秒

最多输入图片

7

目录条目: Vidu 维度AI

最长单段

10 秒

最高分辨率

1080p

帧率

24 fps

原生音频

有 the audio parameter defaults to FALSE on Q2 and Q1, against TRUE on Q3 — the same field, opposite default

生成模式

T2V · I2V · FL2V · REF2V · V2V v2v on viduq2-pro only, which supports video reference, editing and replacement; with a video attached its reference budget drops from 7 images to 4

开放 API

有

最短单段

1 秒 1-10, default 5

最多输入图片

7 1-7 reference images; 1-4 when a reference video is also supplied

目录条目: Vidu 维度AI

可选时长

5 秒 5 seconds is the only selectable duration on this model

最高分辨率

1080p 1080p is the only option — Q1 cannot generate 540p or 720p

帧率

24 fps

生成模式

T2V · I2V · FL2V · REF2V

价格（国际站）

$0.4 / 条 80 credits per 5-second 1080p clip; off-peak is half. Billed per clip, not per second, unlike Q2 and Q3

开放 API

有

目录条目: Vidu 维度AI

可选时长

4 / 8 秒

最高分辨率

1080p 1080p is reachable at 4s only, where image-to-video offers 360p (default), 720p and 1080p; the 8s option is 720p and nothing else. Pricing bills the 4s 1080p clip as a product ("Vidu 2.0 img2video 4S 1080P", 100 credits / $0.50), and the model map lists 360p, 720p, 1080p for the family.

帧率

32 fps the only Vidu model not at 24 fps

生成模式

I2V · FL2V · REF2V First/last-frame is reachable: the start-end-to-video endpoint accepts vidu2.0, and pricing bills "Vidu 2.0 start-end2video" at four tiers (4s 360p/720p/1080p and 8s 720p). Text-to-video is genuinely absent — that endpoint accepts only viduq3-turbo, viduq3-pro, viduq2 and viduq1. The model map additionally marks Effects/Templates for this model, which is a preset gallery rather than a generation mode and has no code in this vocabulary.

开放 API

有

目录条目: Vidu 维度AI

最长单段

15 秒 t2v and i2v 2-15s; the r2v and videoedit endpoints cap at 10s

最高分辨率

1080p 720P | 1080P, default 1080P on i2v. No 480P tier on 2.7, unlike Wan 2.5 and Wan 3.0

帧率

30 fps

原生音频

有 generates dubbing when no audio is supplied; an audio_url may instead be passed as a lip-sync driver

生成模式

T2V · I2V · FL2V · REF2V · V2V · S2V split across four model IDs — wan2.7-t2v, -i2v, -r2v, -videoedit. Request shapes differ from the 2.6 'legacy protocol' and are not interchangeable

价格（国际站）

$0.15 / 秒 1080P; 720P $0.10/s. Same rate across t2v, i2v, r2v and videoedit. 50s free quota, Singapore only. r2v and videoedit bill INPUT video duration in addition to output

开放 API

有

开源权重

无 the Wan-Video GitHub organisation publishes model repositories for 2.1 and 2.2 only — there is no 2.5, 2.6, 2.7 or 3.0 weights repository. 'Wan is open source' is true of the 2022-2.2 line and false of everything currently sold

最短单段

2 秒

反向提示词

有 negative_prompt, maximum 500 characters

最多输入图片

2 first_frame + last_frame on wan2.7-i2v

目录条目: Wan 通义万相

最长单段

30 秒

最高分辨率

1080p 480P | 720P | 1080P

帧率

30 fps

原生音频

有

生成模式

T2V · I2V · FL2V · REF2V documented as all-in-one reference — images, videos and audio, plus docx/ppt/pdf files and web links as input

价格（国际站）

$0.2 / 秒 1080P; 720P $0.10/s, 480P $0.05/s. Billed on input plus output video duration combined, not output alone

开放 API

无 flagged Invitational Preview on the price list — the endpoint exists but access is gated, not self-serve. Do not present Wan 3.0 as generally available

最短单段

2 秒

可用区域

Singapore and China (Beijing) only narrower than the rest of the Wan line, which the same price page also lists in Frankfurt, Virginia and Tokyo. The 30s free quota applies in Singapore only

目录条目: Wan 通义万相

最长单段

15 秒 t2v/i2v 2-15s; r2v 2-10s. The US-scoped fork wan2.6-t2v-us accepts only 5 and 10 — same version number, different spec, purely by region

最高分辨率

1080p

帧率

30 fps

原生音频

有 wan2.6 and wan2.5 generate audio by default; on the -flash variants audio is a priced toggle and audio=false halves the rate

生成模式

T2V · I2V · REF2V

价格（国际站）

$0.15 / 秒 1080P; 720P $0.10/s. The -flash variants are far cheaper: wan2.6-i2v-flash is $0.075/s at 1080p with audio, $0.0375/s silent

开放 API

有

最短单段

2 秒

反向提示词

有

目录条目: Wan 通义万相

最长单段

10 秒

可选时长

5 / 10 秒 a fixed set — 2.5 cannot do free-form durations, unlike 2.6 and 2.7

最高分辨率

1080p 480P | 720P | 1080P, default 1920x1080

帧率

30 fps

原生音频

有

生成模式

T2V · I2V

价格（国际站）

$0.15 / 秒 1080P; 720P $0.10/s, 480P $0.05/s

反向提示词

有

目录条目: Wan 通义万相

可选时长

5 秒 the hosted t2v/i2v/kf2v endpoints are fixed at 5 seconds. The separate wan2.2-animate-move / -animate-mix character-animation endpoints run 2-30s at 15/25 fps

最高分辨率

1080p hosted wan2.2-t2v-plus is 480P and 1080P (no 720P); -i2v-flash and -kf2v-flash add 720P. The OPEN checkpoint is a different configuration — its own repo documents 480P and 720P, with TI2V-5B at 720P

帧率

30 fps hosted API. The open TI2V-5B checkpoint is documented at 24 fps — the served model and the downloadable model are NOT the same configuration

原生音频

无 'No audio' on every hosted wan2.2 video endpoint; the open S2V-14B checkpoint is speech-DRIVEN (audio in), not audio-generating

生成模式

T2V · I2V · FL2V · S2V s2v is open-weights only (S2V-14B); the hosted endpoints are t2v/i2v/kf2v plus the animate pair

价格（国际站）

$0.1 / 秒 hosted wan2.2-t2v-plus at 1080P; 480P $0.02/s. wan2.2-i2v-flash is $0.036/s at 720P. Zero if you self-host the open weights

开源权重

有 five checkpoints: T2V-A14B, I2V-A14B, TI2V-5B, S2V-14B, Animate-14B. This is the NEWEST open Wan release — 2.5 onward is API-only

许可协议

Apache-2.0

目录条目: Wan 通义万相

最长单段

10 秒 the README benchmarks 10-second 720p synthesis; the reference CLI's --video_length defaults to 121 frames (5s at 24fps) and takes a free-form frame count, so 10s is the longest length the vendor documents rather than a selectable preset

最高分辨率

720p native checkpoints are 480p and 720p only; the 1080p figure people quote is a SEPARATE few-step super-resolution network applied afterwards, not a generation resolution

帧率

24 fps

原生音频

厂商未公布 no audio component is documented in the repo or the model card; the card lists video output only

生成模式

T2V · I2V

开放 API

厂商未公布 Tencent publishes no self-serve API tied to this checkpoint. Tencent Cloud sells a separate hosted 混元生视频 product, priced at 1.5 credits per 720p 5s call, but never states which model version backs it — so it cannot be attributed to HunyuanVideo 1.5

开源权重

有

许可协议

Tencent Hunyuan Community License the licence text opens by excluding the EU, UK and South Korea from its Territory — 'open weights' and 'usable in the EU' are different claims here

可用区域

global excl. EU/UK/KR licence-gated, not service-gated: the weights download anywhere, but the grant does not extend to those three territories

反向提示词

有 in the reference inference script (--negative_prompt); Tencent ships no first-party hosted API for this checkpoint

发布 2025-11-20

目录条目: Hunyuan Video 混元视频

最长单段

5 秒 129 frames

最高分辨率

720p 720x1280 / 1280x720 / 1104x832 / 832x1104 / 960x960; a 540p tier also exists

生成模式

T2V the base 13B model is text-to-video; image-to-video ships as a separate checkpoint, HunyuanVideo-I2V. The 1.5 line lives in a SEPARATE repository, not a branch of this one

开源权重

有

许可协议

Tencent Hunyuan Community License same EU/UK/South Korea territorial exclusion as 1.5

发布 2024-12-03

目录条目: Hunyuan Video 混元视频

最长单段

10 秒

可选时长

5 / 10 秒

最高分辨率

4K the size enum is a fixed list — 1280x720, 720x1280, 1024x1024, 1920x1080, 1080x1920, 2048x1080, 3840x2160. 4K means that last member, not arbitrary resolution

帧率

60 fps enum 30 or 60, default 30

原生音频

有 with_audio defaults to false, and the docs describe it as 生成 AI 音效 — sound effects, not dialogue or speech

生成模式

T2V · I2V · FL2V

价格（国内站）

¥1 / 条 1 元/次 on the CN platform bigmodel.cn — flat per call regardless of duration or resolution. The international platform z.ai prices the SAME model id at $0.2/video

开放 API

有

最短单段

5 秒

水印

optional watermark_enabled defaults TRUE and applies both a visible AI mark and an implicit digital watermark, described as 符合政策要求. Turning it off requires a signed disclaimer through 个人中心-安全管理-去水印管理 — not freely switchable

可用区域

global, on two separately-billed platforms bigmodel.cn for CN in CNY and docs.z.ai internationally in USD — same model id, different endpoint host and price

反向提示词

无 read against the full request schema — no negative-prompt parameter exists on any video model on the platform

最多输入图片

2 first/last-frame mode: first image is the first frame, second is the last; each at most 5MB

目录条目: Zhipu Qingying 智谱清影 (CogVideoX)

最高分辨率

4K size enum 720x480, 1024x1024, 1280x960, 960x1280, 1920x1080, 1080x1920, 2048x1080, 3840x2160

帧率

60 fps enum 30 or 60

生成模式

T2V · I2V single input image only — no first/last-frame mode, unlike CogVideoX-3

价格（国内站）

¥0.5 / 条

开放 API

有

最多输入图片

1

目录条目: Zhipu Qingying 智谱清影 (CogVideoX)

最长单段

10 秒 5-10s; frame counts must satisfy 16N+1 with N at most 10

最高分辨率

1360x768 the I2V variant accepts variable resolution with a minimum side of 768 and a maximum of 1360

帧率

16 fps

生成模式

T2V · I2V

开源权重

有 this is the NEWEST open checkpoint — there are no open weights for CogVideoX-2 or CogVideoX-3, so 'CogVideoX is open source' is true of the 2024 line and false of everything currently sold. The repo also MOVED, from THUDM/CogVideo to zai-org/CogVideo

许可协议

CogVideoX LICENSE the 5B-class T2V and I2V transformer weights are under the bespoke CogVideoX LICENSE; only the smaller CogVideoX-2B is Apache-2.0

发布 2024-11-08

目录条目: Zhipu Qingying 智谱清影 (CogVideoX)

最长单段

15 秒

最高分辨率

1080p quality enum 360p, 540p, 720p, 1080p

帧率

厂商未公布 PixVerse exposes no fps parameter and publishes no output frame rate anywhere in the platform docs — duration, quality and aspect_ratio are the only output controls

原生音频

有 opt-in via generate_audio_switch, default FALSE, and it raises the credit rate (1080p goes 19 to 24 credits/s). 'Has native audio' is true; 'generates audio by default' is not

生成模式

T2V · I2V · FL2V · REF2V the vendor names them Text-to-video, Image-to-video, Transition and Fusion

价格（国际站）

$0.01 / 积分 $10 = 1,000 credits at the smallest pack. C1 bills per second: 360p 6 cr/s, 540p 8, 720p 10, 1080p 19 silent; 8/10/13/24 with audio. A 5s 1080p clip with audio is 120 credits, about $1.20

开放 API

有

最短单段

1 秒

水印

optional the API exposes a water_mark boolean. The consumer free-tier watermark is widely reported by third parties but appears on no PixVerse-owned page, so only the API parameter is recorded

可用区域

global the vendor states the platform serves creators across 175 countries; no per-region model gating is documented

反向提示词

有

发布 2026-04-07

目录条目: PixVerse

最长单段

15 秒

最高分辨率

1080p

原生音频

有 switchable across all five modes; generate_audio_switch defaults false

生成模式

T2V · I2V · FL2V · V2V · REF2V vendor names: Text-to-Video, Image-to-Video, Transition, Video Extension, Reference-to-Video. Multi-clip is available on t2v and i2v only

价格（国际站）

$0.01 / 积分 V6 is 5/7/9/18 credits per second at 360p/540p/720p/1080p silent, 7/9/12/23 with audio; Fusion with VIDEO references costs double

开放 API

有

最短单段

1 秒

目录条目: PixVerse

最长单段

10 秒 720p and below; 1080p caps at 8s

可选时长

5 / 8 / 10 秒 1080p cannot use 10s on v5.5/v5.6

最高分辨率

1080p

原生音频

有 generate_audio_switch exists on v5.5, v5.6, v6 and c1 only — NOT on v5 and earlier

价格（国际站）

$0.01 / 积分 V5.6 bills per CLIP, not per second — 5s costs 35/35/45/75 credits at 360p/540p/720p/1080p silent; 10s costs 77/77/99 with no 1080p. The billing MODEL changes at v6, which is what a flat duration column destroys

目录条目: PixVerse