impulse

Wan3.0 Video

Open weightsVideo
API id wan3.0-video
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
3
3 listings
Released
-
date not published

Where to run it

3 hosts serve Wan3.0 Video. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
wan3.0-video
-
wan3.0-video
-
Qwen CloudLab API
wan3.0-video
-

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
AudioImagesTextVideo
Produces
Video
Open weights
License: Apache-2.0
Runtimes: Ollama, SGLang, llama.cpp, vLLM

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller Alibaba Qwen models

No similar Alibaba Qwen model keeps its key capabilities.

Other frontier labs

No similar match from another frontier lab.

Open-weight picks

No similar open-weight match.

Call it

Using Alibaba DashScope's API.

Python
from litellm import completion

response = completion(
    model="dashscope/wan3.0-video",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

Which APIs offer Wan3.0 Video?

Wan3.0 Video runs on 3 APIs: Alibaba DashScope, Qianwen AI Platform and Qwen Cloud.

Is Wan3.0 Video being retired?

No retirement date is scheduled for it on any API we track.

What is Wan3.0 Video's API model id?

Use wan3.0-video with Alibaba DashScope.

Sources

Raw catalog entry for wan3.0-video on Alibaba DashScope
{
  "litellm_provider": "dashscope",
  "mode": "video_generation",
  "source": "https://www.alibabacloud.com/help/en/model-studio/wan3-0-video",
  "output_cost_per_second": 0.165025,
  "output_cost_per_second_480p": 0.041256,
  "output_cost_per_second_720p": 0.082513,
  "output_cost_per_second_1080p": 0.165025,
  "supported_modalities": [
    "text",
    "image",
    "video",
    "audio"
  ],
  "supported_output_modalities": [
    "video"
  ],
  "supported_endpoints": [
    "/v1/videos"
  ],
  "provider_specific_entry": {
    "dashscope_video_reference_input": "first_frame"
  },
  "metadata": {
    "comment": "Wan 3.0 all-in-one video generation (text, first/last frame, multimodal reference, edit, extend). Billed duration is usage.duration, which adds input video seconds for the edit and extend modes. China (Beijing) list price per output second, USD, matching this prefix's default host. The base rate is the 1080P default tier."
  }
}