Home › Models

AI Video & Image Model Profiles (2026): segment length, references, audio and list prices

Specs and list prices of 13 models — Seedance, MiniMax H3, Wan 3.0, Kling, Veo, Sora, Runway Gen-4.5, Vidu, PixVerse V6, SeedDream, Qwen-Image — and which platforms expose them.

Segment length and price

Video models: seconds per generation

9 of 10 video models publish a segment length · longer segments allow more cuts per call
10 video modelsHow we score ↗
Solid = published min–max seconds per generation; ↑ = extendable. Not disclosed: LTX-2.

Published per-second prices (API list + platform prices)

Only prices verifiable on official pages; undisclosed ones are named in the caption
6 verifiable pricesHow we score ↗
  1. PixVerse V6API list price$0.08
  2. Hailuo (MiniMax)platform price$0.08–$0.13
  3. MiniMax Hailuo H3API list price$0.08–$0.13
  4. Wan (Tongyi Wanxiang)platform price$0.09–$0.17
  5. SceneMixerplatform price$0.20–$0.50
  6. Veo 3.1API list price$0.35–$0.75
00.250.50.751
Solid range = published low-to-high tier price per second ($); shorter is cheaper. No convertible per-second price published: LibTV, Xiaoyunque, Dreamina (Jimeng), Kling AI, Vidu, PixVerse, CapCut, LTX Studio, Runway, Pika, Luma Dream Machine, Sora (OpenAI), Veo / Flow (Google), invideo AI, Morph Studio.

Video model spec table

Seedance 2.0 / 2.5MiniMax Hailuo H3Wan 3.0 / 3.0 PrimeKling 3.0 / OmniVeo 3.1SoraRunway Gen-4.5 / AlephViduPixVerse V6LTX-2
Segment length4–15 s (2.0); longer on 2.54–15 s2–30 s5–10 s (extendable)≈ 8 s (extendable)Up to ≈ 20 s (per site)5–10 s4–8 s5–10 s (extendable)Per site
Resolution480p / 720p (2.0); higher on 2.5768p / 2K480p / 720p / 1080pUp to 1080pUp to 1080p / 4K (partial)Up to 1080pUp to 4K via upscaleUp to 1080pUp to 1080pPer site
AudioNative audio (generate_audio)Native speech + ambience; ≤3 reference clips, ≤15 s totalNative audio; dialogue delimited by quotes, 'no dialogue' as control phraseLip-sync; native audio depends on versionNative audio and dialogueWith audioAudio; custom voices (Pro+)LimitedLip-syncPer site
ReferencesFirst/last frame, reference image/video/audio, multimodal≤9 reference images (surcharge beyond 5); first-frame and references are mutually exclusiveReference image/video/audio, freeMulti-element / subject referenceIngredients references, first/last frameImage/video reference, CameoCharacter reference, image-to-videoMulti-subject referenceCharacter consistency referencesCasting references
Intra-segment cutsExecutes multi-shot prompts within one generation3–6 cuts per segment executed reliablyMulti-shot prompts; execution varies by versionSingle-shot orientedSingle-shot; Flow handles continuationStoryboard tool for multi-shotSingle-shotSingle-shotChained on CanvasControlled by LTX Studio's storyboard layer
List priceToken-billed: 2.0 ≈ ¥28 per 1M tokens, 2.5 ≈ ¥42 (+50%)API list: CN ¥0.8/s (2K), ¥0.5/s (768p); international $0.13 / $0.08API ¥1.2/s (1080p), ¥0.6 (720p), ¥0.3 (480p)Membership credits; prices not captured (visible on Runway/Luma pages)Google AI Pro/Ultra credits; API per second ≈ $0.35–0.75/sBundled with ChatGPT Free/Plus/Pro (page returned 403)60 credits per 5 s ≈ 720/min; Standard 625 credits/mo at $15Subscription credits (30 days) / purchased (2 years); prices not capturedAPI $4.80/min (per site)Compute credits within LTX Studio subscription
Where to useVolcengine Ark API, Dreamina, and platforms integrating it (SceneMixer, PixVerse, Runway, Luma)MiniMax API (China / international platforms), Hailuo app, PixVerse, SceneMixerModel Studio API (workspace endpoint), Tongyi site, wan.video, SceneMixerKling China/global sites, API, Runway, Luma, Morph StudioFlow, Gemini API, Vertex AI, Runway, invideosora.com, iOS; API per OpenAIRunway web / APIvidu.com / vidu.cn, APIPixVerse web/iOS/Android/API/CLILTX Studio

All models

ByteDance · 火山引擎 / 即梦 · Video model

Seedance 2.0 / 2.5

ByteDance's video model, available via Volcengine Ark API and Dreamina; 2.5 shipped July 2026 as Pro/Lite/Turbo.

Token-billed: 2.0 ≈ ¥28 per 1M tokens, 2.5 ≈ ¥42 (+50%)Profile →
MiniMax · Video model

MiniMax Hailuo H3

MiniMax's video model: multiple references, reference audio, native speech and intra-segment cuts — a common drama-segment engine.

API list: CN ¥0.8/s (2K), ¥0.5/s (768p); international $0.13 / $Profile →
Alibaba · 阿里云百炼 · Video model

Wan 3.0 / 3.0 Prime

Alibaba's Wan 3.0 video model: up to 30 s per segment, free reference media, audio; Prime is the high-speed tier.

API ¥1.2/s (1080p), ¥0.6 (720p), ¥0.3 (480p)Profile →
Kuaishou · 快手 · Video model

Kling 3.0 / Omni

Kuaishou's Kling video model, known for motion and physics, multi-element reference, integrated by Runway and Luma.

Membership credits; prices not captured (visible on Runway/Luma Profile →
Google DeepMind · Video model

Veo 3.1

Google's video model with native audio and dialogue and strong realism; via Flow, Gemini API/Vertex, Runway and invideo.

Google AI Pro/Ultra credits; API per second ≈ $0.35–0.75/sProfile →
OpenAI · Video model

Sora

OpenAI's video model with audio, Storyboard and Remix; quota via ChatGPT plans.

Bundled with ChatGPT Free/Plus/Pro (page returned 403)Profile →
Runway · Video model

Runway Gen-4.5 / Aleph

Runway's in-house generation (Gen-4.5) and editing (Aleph) models.

60 credits per 5 s ≈ 720/min; Standard 625 credits/mo at $15Profile →
Shengshu · 生数科技 · Video model

Vidu

Shengshu's video model, built around reference-to-video and multi-subject consistency.

Subscription credits (30 days) / purchased (2 years); prices notProfile →
Aishi · 爱诗科技 · Video model

PixVerse V6

PixVerse's flagship in-house model; the platform also offers Seedance 2.5 and MiniMax H3.

API $4.80/min (per site)Profile →
Lightricks · Video model

LTX-2

Lightricks' in-house video model powering LTX Studio.

Compute credits within LTX Studio subscriptionProfile →
ByteDance · 火山引擎 · Image model

SeedDream 5.0

ByteDance's image model (Pro / Lite) with 2K output and strong understanding of Chinese costume terms — a common choice for character sheets and scene plates.

Per image: Pro 2K ¥0.60, Lite ¥0.22Profile →
Alibaba · 阿里云百炼 · Image model

Qwen-Image 3.0 / 3.0 Pro

Alibaba's Qwen-Image 3.0 family: text-to-image and image editing in one model, pixel area up to 2048×2048.

3.0 ¥0.18/image; Pro 1K ¥0.25, 2K ¥0.5; input images ¥0.02 eachProfile →
Google · Image model

Gemini 3 Pro Image / 3.1 Flash Image

Google's image models (Nano Banana family), strong on English prompts and modern settings.

Pro ≈ $0.134/image; Flash ≈ $0.067 (1K)Profile →

Explainer: which video model for short drama →