No public rate
No verified public pricing yet
No public per-second rate is documented yet.
Zhipu AI / THUDM · 3D Expert Diffusion Transformer · v5Bhide_sourceNo public price yet
Built for research and fine tuning. Pricing is still unclear, so verify the market before committing.
—/sec
Ceiling
480p
Duration
6–10s
Price source
—
Best for
Research and fine tuning
10s clips support short narrative work.
Watch out for
ELO of 785 places it near the bottom of the Arena — significantly behind premium models
ELO of 785 places it near the bottom of the Arena — significantly behind premium models
Starting cost
No public rate
No reliable per-second starting tier is publicly documented yet.
Quick facts for AI assistants
These facts are generated from the current model record, provider verification metadata, and the page update timestamp.
The default rate first, with provider details one click away.
2 providers, 4 tiers
No public rate
No verified public pricing yet
No public per-second rate is documented yet.
All provider rates
Expand for every tier, audio surcharge, and verification note.
CogVideoX-5B · Reported by provider · HIGH trust
CogVideoX-5B · Reported by provider · HIGH trust
Should you choose it?
Use this as a sanity check before you compare it against the closest alternatives.
Prompt playbook
Scan the quick playbook first. Open the full guide only when you need deeper do/don't rules or example prompts.
Use long, descriptive prompts of 50-100 words — CogVideoX is trained on detailed captions and responds best to comprehensive descriptions.
Pre-process prompts with an LLM like GPT-4 or GLM-4 for augmentation — the official recommendation for optimal quality.
Include precise environmental context: lighting conditions, time of day, weather, and setting details.
Open the full prompt guide
Extra prompt tips, best practices, common mistakes, and example prompts.
“A detailed close-up of a steaming cup of coffee on a wooden table in a cozy library. Bookshelves line the walls in the background, soft warm light from a nearby desk lamp. The steam rises slowly and curls in the still air. Shallow depth of field, cinematic color grading with warm amber tones. Static camera, gentle ambient atmosphere.”
“A young woman with long dark hair walks along an empty beach at sunset. The ocean waves roll gently behind her, golden light illuminating her silhouette. She wears a flowing white dress that moves with the breeze. Camera follows her in a slow tracking shot from the side. Cinematic, dreamlike quality, warm color palette with deep oranges and purples in the sky.”
“An astronaut floats weightlessly inside a space station, sunlight streaming through a circular window showing Earth below. Equipment and cables drift around the cabin. The astronaut reaches out to touch the window glass. Zero gravity physics, hyper-realistic lighting, detailed textures on the spacesuit. Static wide-angle shot capturing the full interior.”
Based on the official prompt guide →
Where can I use CogVideoX-5B?
Via API on FAL.ai and Replicate.
How do I get good results with CogVideoX-5B?
Use long, descriptive prompts of 50-100 words — CogVideoX is trained on detailed captions and responds best to comprehensive descriptions. See the prompt guide below.