Wan 3.0 API Pricing: ModelGo vs OpenRouter in Four Real Jobs

Before choosing an API platform, compare the output and the bill. These four production briefs cost $3.636364 on ModelGo and $3.400000 on OpenRouter; the results below show the actual outputs and charges.

What Is Wan 3.0?

Wan 3.0 supports text-to-video and first-frame generation through the tested video API. It is a useful candidate for spatial reveals, construction visualizations, vehicle features and game environments where object continuity matters.

Test Method and Actual Charges

We ran four distinct briefs: two text-only and two reference-driven, using matching prompts, reference files and requested settings wherever both platforms were accessible. ModelGo costs were matched to settled billing records and OpenRouter costs come from completed responses’ usage data; the table shows model-output charges rounded to six decimals, excluding separately generated reference art.

Cost scope: these are model-call charges, not the cash outlay required to fund an account. They exclude recharge/payment processing fees, including the 5.5% recharge fee used in the separate pricing comparison; percentage differences here compare call charges only.

Four Production Examples

Modular bridge assembly sequence

Production use: Construction / B2B visualization.

Exact prompt

Create a 10-second architectural visualization of a small prefabricated pedestrian bridge being assembled across a narrow landscaped canal. Use a fixed elevated three-quarter camera with coherent engineering scale. Seconds 0–3: two finished concrete abutments and a clear central gap are visible. Seconds 3–7: a single steel bridge module is lowered slowly by a crane from above until both ends rest on the abutments; the module must remain rigid and correctly aligned. Seconds 7–10: the lifting slings slacken and the camera holds the completed bridge, with two adult workers standing safely on the bank for scale. Use calm overcast daylight. No road traffic, collapsing structures, jumping construction stages, text or safety-certification claims. Deliver one coherent ten-second clip. Avoid speed ramps, unrelated cutaways and abrupt changes in camera direction; preserve the specified subject throughout.

6.95% higher ModelGo charge.

Electric SUV lighting reveal

Production use: Automotive / feature campaign.

Exact prompt

Create a 10-second premium automotive lighting film for an original dark-emerald electric SUV in a minimal concrete studio. Begin with the vehicle stationary in shadow and the camera low at the front-left corner. Seconds 0–3: one continuous front light bar illuminates smoothly from center to edges. Seconds 3–7: the camera moves laterally past the front wheel toward the driver’s door, revealing realistic metallic paint and a stable body silhouette. Seconds 7–10: the cabin ambient light comes on behind the closed window as the camera settles into a side profile. Keep the wheels stationary, panel gaps consistent and reflections coherent. No manufacturer logos, license plates, driving footage, text or performance claims. Deliver one coherent ten-second clip. Avoid speed ramps, unrelated cutaways and abrupt changes in camera direction; preserve the specified subject throughout.

6.95% higher ModelGo charge.

Commuter backpack weather transition

Production use: Bags / retail advertising.

This original reference was used for ModelGo and for the paired OpenRouter request where account access was available.

Exact prompt

Use the supplied original modular commuter backpack as the exact product reference. Preserve its slate-blue fabric, single diagonal front zipper, roll-top closure and orange side loop. Create a 10-second continuous shot beginning with the backpack on a bench under a transit shelter during light rain. Seconds 0–4: a slow camera slide reveals a few droplets on the fabric. Seconds 4–8: the background transitions through a clean match dissolve to a warm modern office, while the backpack stays in the same screen position, shape and scale. Seconds 8–10: a natural adult hand lifts it by the top handle. No additional pockets, changing zippers, invented waterproof ratings, logos or text. Keep the visual transition controlled and useful for a retail campaign. Deliver one coherent ten-second clip. Avoid speed ramps, unrelated cutaways and abrupt changes in camera direction; preserve the specified subject throughout.

6.95% higher ModelGo charge.

Dungeon portal game reveal

Production use: Games / launch teaser.

This original reference was used for ModelGo and for the paired OpenRouter request where account access was available.

Exact prompt

Animate the supplied original stone dungeon doorway into a 10-second game teaser. Preserve its six carved arch stones, shallow steps, two bronze sconces and central circular seal. Seconds 0–4: the camera slowly approaches the doorway as dust moves through narrow torchlight. Seconds 4–7: the circular seal rotates one quarter turn and the two stone door panels slide apart, revealing a restrained violet portal inside the same opening. Seconds 7–10: the portal light illuminates the existing carvings and the camera stops before crossing the threshold. Keep architecture rigid, lighting coherent and particle density low. No monsters, violence, licensed symbols, text or new architectural wings appearing. Prioritize a readable environmental reveal over frantic motion. Deliver one coherent ten-second clip. Avoid speed ramps, unrelated cutaways and abrupt changes in camera direction; preserve the specified subject throughout.

6.95% higher ModelGo charge.

How to Calculate the Saving

For outputs with matching delivered specifications, calculate the reduction as (OpenRouter actual charge − ModelGo settled charge) / OpenRouter actual charge × 100. Use the returned dimensions, duration and audio track when deciding whether two outputs are comparable.

Start with the ModelGo API

Install requests and set MODELGO_API_KEY in your environment. The code below uses the endpoint, model ID and parameters from the first real example, with its exact prompt embedded directly. This example submits an asynchronous video job; polling and download steps are described below the code.

import os, requests

prompt = 'Create a 10-second architectural visualization of a small prefabricated pedestrian bridge being assembled across a narrow landscaped canal. Use a fixed elevated three-quarter camera with coherent engineering scale. Seconds 0–3: two finished concrete abutments and a clear central gap are visible. Seconds 3–7: a single steel bridge module is lowered slowly by a crane from above until both ends rest on the abutments; the module must remain rigid and correctly aligned. Seconds 7–10: the lifting slings slacken and the camera holds the completed bridge, with two adult workers standing safely on the bank for scale. Use calm overcast daylight. No road traffic, collapsing structures, jumping construction stages, text or safety-certification claims. Deliver one coherent ten-second clip. Avoid speed ramps, unrelated cutaways and abrupt changes in camera direction; preserve the specified subject throughout.'
headers = {"Authorization": "Bearer " + os.environ["MODELGO_API_KEY"]}
headers["X-DashScope-Async"] = "enable"
payload = {'model': 'wan3.0-video',
 'input': {'prompt': prompt},
 'parameters': {'resolution': '720P', 'duration': 10, 'ratio': '16:9', 'audio': False}}
response = requests.post('https://api.modelgo.ai/api/v1/services/aigc/video-generation/video-synthesis', headers=headers, json=payload, timeout=420)
response.raise_for_status()
result = response.json()
print(result)  # Save the returned task ID for polling.

After submission, retain output.task_id from the response and poll GET https://api.modelgo.ai/api/v1/tasks/{task_id} until the task reaches a terminal state. Once successful, download the video using output.video_url from the response.

Audio request versus delivery: the recorded requests on both platforms set the audio flag to false. The returned files nevertheless contain an audio stream. “Audio present” describes the detected file structure, not confirmation of audible sound or successful audio control. The code preserves the actual request; these tests do not establish why the audio flag was not reflected in the delivered file.

For first-frame generation on this route, add an input.media entry with type: "first_frame" and a url containing the reference image.

ModelGo and OpenRouter use different model IDs and media request formats. Reuse the production brief, but adapt the endpoint, reference-image structure, task polling and download handling following each platform’s documented request format.

ModelGo API documentation

Use Wan 3.0 on ModelGo

To use Wan 3.0, the model featured in this guide, visit the ModelGo Models page.

Explore Wan 3.0 on ModelGo

Sources and Further Reading

These references cover model capabilities, interfaces and usage records; the briefs were written independently for this test.

• Official model documentation or family showcase: Model capabilities and creative reference; related family documentation is not a specification guarantee for a different variant.
• OpenRouter API reference: Request conventions and platform differences.
• OpenRouter usage accounting: How usage information is exposed; the amounts in this article come from the recorded test calls.
• OpenRouter model catalog API: Check model IDs and catalog properties before a new integration.
• OpenRouter video generation guide: Media request structure and supported workflow patterns.