Alibaba

Wan 2.2 A14BAperto

Alibaba’s open-weight MoE video-diffusion model — cinematic 1080p text-to-video and image-to-video.

#33rilasciato il 15 set 2026·Open Weights·27B (14B active MoE)
textvideo64K ctx
Provider APIOttieni chiave API →Classifica
Intelligenza
87.4 #33
AAQI 87.0
Velocità Uscita
15 t/s
ITL 66.7 ms/tok
Prezzo combinato (3:1)
$0.06 /1M
Input $0.06/M · Output $0.06/M
Contesto
64K
≈ 160 pagine A4 · output max 2,048

Quality Domain Radar

6-Axis Frontier Evaluation vs Category Average & Flagship

Wan 2.2 A14B
Claude Mythos Preview (#1)
Average (68)
Coding (15)Mathematics (15)Hard Science (GPQA) (35)Agentic & Tool Use (20)Knowledge (MMLU) (55)Vision / Multimodal (96)

Gli assi radar sono approssimati dai punteggi di categoria dove mancano misurazioni dirette — vedi Metodologia.

Punti di forza e compromessi

Dove vince

  • Best open-weight video model — rivals Kling/Veo tiers
  • Consumer-GPU serving — ~18GB at Q4
  • Strong prompt adherence on complex motion
  • Free to self-host and fine-tune

A cosa fare attenzione

  • Multi-second clips only — no long-form generation
  • Slow sampling — minutes per clip without distillation
  • No native audio track

Casi d'uso killer

Marketing & product clips
Short cinematic b-roll and product loops from prompts.
Storyboarding pipelines
Rapid previz for film and ad concepts.
Self-hosted video APIs
Own the full generation stack — no per-clip vendor fees.

Quickstart per sviluppatori e API

Imposta prima DASHSCOPE_API_KEY — ottieni una chiave API
curl https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions \
  -H "Authorization: Bearer $DASHSCOPE_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "wan2.2-t2v-a14b",
    "messages": [{"role": "user", "content": "Refactor this function for O(n) time and explain the change."}]
  }'

Risorse e link ufficiali

Deployment API

Confronta host e latenza

Throughput, TTFT e prezzi cache su Groq, Cerebras, Together, DeepInfra, Fireworks, Bedrock e Azure.

GroqCerebrasTogether AIDeepInfraFireworks AIAWS BedrockAzure AI
Vedi matrice provider →

Punteggi per Fonte

Specifiche live e architettura

Sotto il cofano
Wan 2.2 A14B — MoE video diffusion, 14B active
  • High/low-noise expert pair — 14B active per denoising step
  • Cinematic training corpus — film-grade lighting and camera control
  • Text-to-video and image-to-video from one checkpoint
  • Runs on a single 24GB consumer GPU at Q4
Data di Rilascio
15 set 2026
Architettura
Wan 2.2 A14B — MoE video diffusion, 14B active
Parametri
27B (14B active MoE)
Licenza
Open Weights
Finestra di Contesto
64,000 tokens
Output max
2,048 tokens
Modalità
text + video
Prezzi cache
lettura $0.01 · scrittura $0.08 /1M
Ragionamento
—
Prezzo Ingresso
$0.06/M
Prezzo Uscita
$0.06/M
Velocità Uscita
15 t/s
Tempo al Primo Token
—
Dati aggiornati
22 ott 2026
Hardware e inferenza locale
Dati: Convly AI (CC BY 4.0) ↗
VRAM (4-bit Q4)
18 GB
GPU min.
RTX 4090 24GB / RTX 5090 32GB

Stima bolletta mensile

Spesa mensile stimata
$0.00
Calcolo risparmio vs GPT-4o…

Cita e incorpora

Badge Markdown GitHub
Loading badge markdown...
BibTeX
@misc{llmpodium2026wan22a14b,
  title = {Benchmark Analysis and Intelligence Evaluation of Wan 2.2 A14B},
  author = {LLMPodium Research},
  year = {2026},
  url = {https://llmpodium.com/models/wan-2-2-a14b}
}

Incorpora il badge del punteggio

Aggiungi un badge Podium Score live al tuo README su GitHub o Hugging Face — rimanda alla classifica live.

Anteprima
Wan 2.2 A14B LLMPodium Score
Markdown
Loading badge snippet...
HTML
Loading badge snippet...

Altri modelli di Alibaba

Modelli alternativi

Migliori alternative a Wan 2.2 A14B in base a capacità, prezzi e benchmark.

0 / 4