Alibaba AI Models
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 all providers
- No separate %{provider} account required
- Model skills carry docs, schemas, and setup steps into your workspace
- Per-call billing in USD, no subscription or minimum spend
- Failed generations are never charged
- Switch models by changing one parameter
- Billing consolidated into one monthly invoice
What stands out
One of the most-used model APIs from Alibaba, chosen by developers for its balance of output quality, speed, and pricing.
One of the most-used model APIs from Alibaba, chosen by developers for its balance of output quality, speed, and pricing.
Lowest starting price across the Alibaba catalog, suited for high-volume workflows and cost-sensitive production pipelines.
All Alibaba models available through RunAPI
HappyHorse API access for text, image, and edit-video generation with 720p/1080p output and character-guided clips.
Alibaba Qwen API access via RunAPI — Apache-2.0 ultra-sparse MoE with 262K context, 80B total / 3.9B active.
Qwen 2 API access for text-to-image, image remix, and image editing from Alibaba's visual model family.
Wan API access for a video and image suite covering text-to-video, image-to-video, video editing, and storyboards.
Z Image API access for ultra-fast text-to-image, photorealistic results, and short inference paths.
Install a Alibaba model skill for your app.
Pick a model and add its skill so your coding tool has docs, schemas, pricing notes, and setup steps. Skills work with Claude Code, Codex, Gemini CLI, Cursor, and VS Code. Install once, then switch models by changing one parameter.
curl -X POST https://runapi.ai/api/v1/happyhorse/text_to_video \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "happyhorse-text-to-video",
"prompt": "Generate a 5-second 1080p cinematic clip of a paper horse galloping through a miniature cardboard city at night."
}'import { HappyhorseClient } from "@runapi.ai/happyhorse";
const client = new HappyhorseClient();
const result = await client.textToVideo.run({
model: "happyhorse-text-to-video",
prompt: "Generate a 5-second 1080p cinematic clip of a paper horse galloping through a miniature cardboard city at night.",
});<?php
require __DIR__ . "/vendor/autoload.php";
use RunApi\Happyhorse\HappyhorseClient;
$client = new HappyhorseClient();
$result = $client->textToVideo->run([
'model' => 'happyhorse-text-to-video',
'prompt' => 'Generate a 5-second 1080p cinematic clip of a paper horse galloping through a miniature cardboard city at night.',
]);require "runapi/happyhorse"
client = RunApi::Happyhorse::Client.new
result = client.text_to_video.run(
model: "happyhorse-text-to-video",
prompt: "Generate a 5-second 1080p cinematic clip of a paper horse galloping through a miniature cardboard city at night."
)npx skills add runapi-ai/happyhorse -g# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
# Codex
codex plugin install runapi-mcp@agents
# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursorEvery Alibaba variant with pricing and model IDs
| Model | Variant | Billing | From | |
|---|---|---|---|---|
|
HappyHorse
|
happyhorse-character | second | $0.480 | View → |
| happyhorse-edit-video | second | $0.480 | View → | |
| happyhorse-image-to-video | second | $0.480 | View → | |
| happyhorse-text-to-video | second | $0.480 | View → | |
|
Qwen 2
|
qwen-2-edit-image | call | $0.060 | View → |
| qwen-2-remix-image | call | $0.040 | View → | |
| qwen-2-text-to-image | call | $0.060 | View → | |
|
Wan
|
wan-2.2-a14b-image-to-video-turbo | call | $0.400 | View → |
| wan-2.2-a14b-speech-to-video-turbo | second | $0.240 | View → | |
| wan-2.2-a14b-text-to-video-turbo | call | $0.400 | View → | |
| wan-2.2-animate-move | second | $0.130 | View → | |
| wan-2.2-animate-replace | second | $0.130 | View → | |
| wan-2.5-image-to-video | second | $0.120 | View → | |
| wan-2.5-text-to-video | second | $0.120 | View → | |
| wan-2.6-edit-video | second | $0.140 | View → | |
| wan-2.6-flash-edit-video | call | $0.300 | View → | |
| wan-2.6-flash-image-to-video | call | $0.300 | View → | |
| wan-2.6-image-to-video | second | $0.140 | View → | |
| wan-2.6-text-to-video | second | $0.140 | View → | |
| wan-2.7-edit-video | second | $0.160 | View → | |
| wan-2.7-image | call | $0.050 | View → | |
| wan-2.7-image-pro | call | $0.120 | View → | |
| wan-2.7-image-to-video | second | $0.160 | View → | |
| wan-2.7-r2v | second | $0.160 | View → | |
| wan-2.7-text-to-video | second | $0.160 | View → |
Frequently asked questions about Alibaba
Is this an official Alibaba integration?
RunAPI exposes a managed API surface with transparent per-call pricing, fully documented capability and parameters, and clear error behavior. You get the same model output quality without managing a direct provider relationship or provider-side account.
Do I need a Alibaba account?
No. Your RunAPI API key is enough for managed access to all Alibaba models. You do not need to create a separate account, manage provider-specific credentials, or handle provider-side billing.
What's the latency overhead from proxying through RunAPI?
Typically under 20 ms. RunAPI keeps the proxy layer close to model execution regions to minimize added latency. Media generation time is dominated by the model itself, not the proxy.
Are images / videos cached?
Generated outputs are stored and retrievable by task ID. You can fetch completed results at any time using the task status endpoint or the RunAPI dashboard. Output URLs remain accessible for the retention period shown in the API docs. Inputs are not cached or stored.
Can I bring my own key?
Not currently. Calls use RunAPI-managed access, which simplifies authentication and lets RunAPI handle rate limiting, retries, and billing consolidation on your behalf.
How is billing consolidated?
All API calls across all providers appear on a single monthly USD invoice. There is no per-provider billing, no subscription, and no minimum spend. Failed generations are never charged.
What SDKs can I use with Alibaba models?
Official SDKs are available for Python, Node.js, PHP, Java, Ruby, and Go. Each SDK handles authentication, async task polling, and typed responses. For LLM models, the OpenAI and Anthropic SDKs also work by pointing the base URL to RunAPI.
What are model skills and how do they work?
Model skills are installable packages that load a model's docs, typed schemas, pricing notes, and setup steps directly into your coding workspace. Install a skill with one command and your agent has the right context before you write integration code. Skills work with Claude Code, Codex, Gemini CLI, Cursor, and VS Code.
How do I switch between Alibaba models?
Change the model parameter in your API request. All Alibaba models share the same API key, the same request shape, and the same billing. No code changes, no re-authentication, and no separate billing setup are required when switching between models or between variants of the same model. You can also switch to models from other providers by changing the same parameter — the API surface is unified across the entire catalog.
