Alibaba
Wan video generation, Qwen image models, and Z Image — Alibaba's full creative AI stack.
Alibaba ships a comprehensive suite of creative AI models: Wan for video and image generation including text-to-video, image-to-video, and video editing; Qwen 2 for image generation and editing; and Z Image for ultra-fast photorealistic text-to-image.
- Single API key shared across providers
- Per-call billing, no commitment
- Gerações com falha não são cobradas
- Streaming supported where the model supports it
What stands out
All models from Alibaba
Text, image, and edit-video generation with 720p and 1080p output, duration control, first-frame image support, ordered reference images for character-guided clips, and source-video editing.
Text-to-image, image remix, and image editing from Alibaba's Qwen visual model family.
Comprehensive video and image suite — text-to-video, image-to-video, video editing, and storyboards.
Ultra-fast text-to-image — photorealistic results in ~1 second with 8 inference steps.
Start with any Alibaba model.
Pick a model, install the skill, and start calling from any agent.
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/happyhorse -gInstall the HappyHorse skill for me: 1. Clone https://github.com/runapi-ai/happyhorse 2. Copy the skills/happyhorse/ directory into your user-level skills directory (e.g. ~/.claude/skills/ for Claude Code, ~/.codex/skills/ for Codex). 3. Verify that SKILL.md is present. 4. Confirm the install path when done.
Every variant from Alibaba
| Model | Variant | Billing | From | |
|---|---|---|---|---|
|
HappyHorse
|
happyhorse-character | second | $0.480 | Ver → |
| happyhorse-edit-video | second | $0.480 | Ver → | |
| happyhorse-image-to-video | second | $0.480 | Ver → | |
| happyhorse-text-to-video | second | $0.480 | Ver → | |
|
Qwen 2
|
qwen-2-edit-image | call | $0.040 | Ver → |
| qwen-2-remix-image | call | $0.040 | Ver → | |
| qwen-2-text-to-image | call | $0.060 | Ver → | |
|
Wan
|
wan-2.2-a14b-image-to-video-turbo | call | $0.400 | Ver → |
| wan-2.2-a14b-speech-to-video-turbo | second | $0.240 | Ver → | |
| wan-2.2-a14b-text-to-video-turbo | call | $0.400 | Ver → | |
| wan-2.2-animate-move | second | $0.130 | Ver → | |
| wan-2.2-animate-replace | second | $0.130 | Ver → | |
| wan-2.5-image-to-video | second | $0.120 | Ver → | |
| wan-2.5-text-to-video | second | $0.120 | Ver → | |
| wan-2.6-edit-video | second | $0.140 | Ver → | |
| wan-2.6-flash-edit-video | call | $0.300 | Ver → | |
| wan-2.6-flash-image-to-video | call | $0.300 | Ver → | |
| wan-2.6-image-to-video | second | $0.140 | Ver → | |
| wan-2.6-text-to-video | second | $0.140 | Ver → | |
| wan-2.7-edit-video | second | $0.160 | Ver → | |
| wan-2.7-image | call | $0.050 | Ver → | |
| wan-2.7-image-pro | call | $0.120 | Ver → | |
| wan-2.7-image-to-video | second | $0.160 | Ver → | |
| wan-2.7-r2v | second | $0.160 | Ver → | |
| wan-2.7-text-to-video | second | $0.160 | Ver → |
Frequently asked questions about Alibaba
Is this an official Alibaba integration?
RunAPI exposes a managed API surface with transparent pricing, capability, and error behavior.
Do I need a Alibaba account?
No. Your RunAPI key is enough for managed access.
How is pricing billed?
Per-call or per-unit metered, with failed generations not charged.
