TheRouter.aiTheRouter.ai
Back to Models

Vidu Q1 Text-to-Video

zhipuzhipu/viduq1-text

Zhipu AI Vidu Q1 Text-to-Video β€” 5s 1920Γ—1080 video from text prompt.

Vidu Q1 model guide β€” Zhipu AI official docs β†—Video generation async API β€” Zhipu AI official docs β†—

Vidu Q1 Text is Zhipu AI's text-to-video mode in the Vidu Q1 generation. It accepts a text prompt and an optional style flag, then generates a fixed 5-second, 24 fps, 1080p video with no image anchor required. The Q1 generation focuses on high-quality video creation: sharper image texture, fewer hand-intersection artifacts, reduced frame shake, stronger realistic-scene fidelity, and precise 2D animation style retention. Within the Vidu Q1 family, viduq1-text is the pure prompt-driven option; when you also have a first frame, use viduq1-image, and when both endpoints are known, use viduq1-start-end.

The model supports two style modes via the style parameter: "general" for photorealistic and cinematographic output, and "anime" for 2D animation styles including Chinese-style and Japanese-style hand-drawn aesthetics. Through TheRouter, use the public model id zhipu/viduq1-text; operational pricing and routed parameters come from the model catalog, while the official upstream API names the model viduq1-text and is served at open.bigmodel.cn/api/paas/v4/videos/generations.

Best for
  • β€’ Concept-to-video generation from a text description alone, without any reference or anchor images
  • β€’ Anime and 2D animation shorts where the style parameter can be set to "anime" for precise style retention
  • β€’ Film, advertising, and cultural-tourism promotional clips driven by descriptive prompts at 1080p resolution
  • β€’ Short-drama and narrative storyboarding where each scene is defined by a prompt and no visual assets are yet available
Reach for something else if
  • β€’ Video from an existing image anchor β€” route to zhipu/viduq1-image when a first frame is available
  • β€’ Controlled transitions between two fixed frames β€” route to zhipu/viduq1-start-end when both endpoints are known
  • β€’ Long clips or variable-duration timelines β€” Vidu Q1 Text is documented as fixed 5-second output
  • β€’ Tasks requiring verified snippets today β€” code examples remain unproven until a human approves a funded snippet verification run

How TheRouter serves this differently from the vendor

As the vendor operates it

Zhipu's native MaaS API exposes Vidu Q1 Text at /api/paas/v4/videos/generations using upstream model name viduq1-text. The official call example accepts model, style ("anime" or "general"), prompt, duration, aspect_ratio, size, and movement_amplitude.

On TheRouter

TheRouter serves the same text-to-video capability under public id zhipu/viduq1-text through its routed video-generation surface with unified TheRouter auth, pricing, and parameter catalog.

docs.bigmodel.cn β†—
Context Length
--
Max Output
--
Request Priceper request
$0.432/ request

Modalities

text→video

Capabilities

Text to Video

Media Generation Capabilities

video_generation
sizes
  • 1920x1080
durations_seconds
  • 5
defaults
size
1920x1080
duration_seconds
5

Pricing Breakdown

TypeRate
Request$0.432 / request

Supported Parameters

promptstyleaspect_ratiodurationsizemovement_amplitude

Specifications

Generation modeText to videodocs.bigmodel.cn β†—verified
Style parameter"general" (realistic/cinematic) or "anime" (2D animation, includes Chinese-style and Japanese-style hand-drawn)docs.bigmodel.cn β†—verified
Duration5 secondsdocs.bigmodel.cn β†—verified
Frame rate24 fpsdocs.bigmodel.cn β†—verified
Output resolution1080p / 1920Γ—1080docs.bigmodel.cn β†—verified
Upstream model nameviduq1-textdocs.bigmodel.cn β†—verified
Upstream list priceΒ₯2.5 per requestdocs.bigmodel.cn β†—verified
Generated URL validity1 daydocs.bigmodel.cn β†—verified
Concurrent in-flight tasksV0: 5, V1: 10, V2: 15, V3: 20docs.bigmodel.cn β†—verified

Benchmarks

BenchmarkDistributionScoreSource
Official qualitative quality claims
Zhipu describes stronger image clarity, fewer hand-intersection artifacts, reduced frame shake, near-realistic style, and better 2D animation style retention for Q1 across all modes. No numeric benchmark table is published.
Not numerically discloseddocs.bigmodel.cn β†—
Style modes
The official guide explicitly lists two style options for viduq1-text: "general" for realistic/cinematic and "anime" for 2D animation including Chinese-style (ε›½ζΌ«) and Japanese-style (ζ—₯ζΌ«) hand-drawn aesthetics.
general + animedocs.bigmodel.cn β†—
Output specification
The official Vidu Q1 overview lists all three modes β€” image, start-end, and text β€” as fixed 5-second, 24 fps, 1080p output. The text-to-video call example uses duration 5, aspect_ratio 16:9, and size 1920x1080.
5s / 24 fps / 1080pdocs.bigmodel.cn β†—

API Usage Examples

Use the global api.therouter.ai endpoint shown below for new integrations; the legacy China accelerated endpoint is retired.

cURL
curl https://api.therouter.ai/v1/videos   -H "Content-Type: application/json"   -H "Authorization: Bearer $THE_ROUTER_API_KEY"   -d '{
    "model": "zhipu/viduq1-text",
    "prompt": "A slow tracking shot through a neon-lit city street",
    "duration": 8
  }'

API guide

Full API reference β†’

Async text-to-video task

Submit a text prompt to generate a fixed 5-second 1080p video. Use the style parameter to choose between realistic and anime output. Snippets are illustrative only until human-approved verification is funded.

cURL
curl https://api.therouter.ai/v1/videos \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zhipu/viduq1-text",
    "prompt": "Peter Rabbit drives a tiny car through a sunny market, happy and joyful expression, cinematic lighting",
    "style": "general",
    "duration": 5,
    "aspect_ratio": "16:9",
    "size": "1920x1080",
    "movement_amplitude": "auto"
  }'

More from zhipu

zhipu/viduq1-imageUse when a first-frame image is available to anchor the generated motionzhipu/viduq1-start-endUse when both the first and last frame are known β€” for controlled 5-second 1080p transitionszhipu/vidu2-imageLower-cost Vidu 2 image-to-video option at 720p for high-volume production runs

Similar models

Cross-provider sibling models
doubao/doubao-seedance-2-0
Higher-end video model when you need native audio and broader multimodal controls
doubao/doubao-seedance-2-0-fast
Fast video-drafting alternative when lower cost matters more than Zhipu Q1 quality

News & changes

2025-06-18

Zhipu documents Vidu Q1 Text for 5-second 1080p text-to-video generation

The official Vidu Q1 guide describes image-to-video, start-end-frame, and text-to-video modes, all fixed at 5 seconds, 24 fps, and 1080p. The text mode accepts a prompt plus an optional style parameter β€” "general" for cinematic realism, "anime" for 2D hand-drawn styles β€” and is positioned for film, advertising, short drama, and cultural-tourism content.

re-authored by TheRouterdocs.bigmodel.cn β†—

Frequently asked

What does the style parameter do in viduq1-text?

Setting style to "general" generates photorealistic and cinematic output suited for live-action scenes, product shots, and city footage. Setting it to "anime" generates 2D animation output that can reproduce Chinese-style and Japanese-style hand-drawn aesthetics. The official guide shows the anime call using "anime" and the realistic call using "general".

re-authored by TheRouterdocs.bigmodel.cn β†—
How long and what resolution are viduq1-text outputs?

All Vidu Q1 modes, including text-to-video, are fixed at 5 seconds, 24 fps, and 1080p. The official call example uses duration: 5 and size: "1920x1080".

re-authored by TheRouterdocs.bigmodel.cn β†—
Are the snippets on this page verified against the live API?

No. This scheduled curation run has no paid API budget, and snippet verification requires an operator-set approval flag. Treat the snippets as integration-shaped examples until a human funds and approves verification.

re-authored by TheRouterdocs.bigmodel.cn β†—
Fact ledger β€” every claim on this page traces here
sourceURLretrieved
Generation modedocs.bigmodel.cn β†—2026-09-16verified
Style parameterdocs.bigmodel.cn β†—2026-09-16verified
Durationdocs.bigmodel.cn β†—2026-09-16verified
Frame ratedocs.bigmodel.cn β†—2026-09-16verified
Output resolutiondocs.bigmodel.cn β†—2026-09-16verified
Upstream model namedocs.bigmodel.cn β†—2026-09-16verified
Upstream list pricedocs.bigmodel.cn β†—2026-09-16verified
Generated URL validitydocs.bigmodel.cn β†—2026-09-16verified
Concurrent in-flight tasksdocs.bigmodel.cn β†—2026-09-16verified
Official qualitative quality claimsdocs.bigmodel.cn β†—2026-09-16verified
Style modesdocs.bigmodel.cn β†—2026-09-16verified
Output specificationdocs.bigmodel.cn β†—2026-09-16verified
Zhipu documents Vidu Q1 Text for 5-second 1080p text-to-video generationdocs.bigmodel.cn β†—2026-09-16verified
What does the `style` parameter do in viduq1-text?docs.bigmodel.cn β†—2026-09-16to verify
How long and what resolution are viduq1-text outputs?docs.bigmodel.cn β†—2026-09-16to verify
Are the snippets on this page verified against the live API?docs.bigmodel.cn β†—2026-09-16to verify
Help & contact