Image & Video Generation APIs from China: gpt-image-2 to Hailuo

Text-to-image and video generation models are now good enough to sit inside real products — marketing pipelines, e-commerce listings, game assets, short-form video. The catch for developers in China is familiar: the strongest models live behind billing pages that want a foreign card and endpoints that are unreliable or unreachable from Mainland networks.

This guide covers what actually works in August 2026: generating images with gpt-image-2, Gemini 3 Pro Image and Gemini 3.1 Flash Image (the line the community searches as "Nano Banana"), Doubao Seedream, and Grok Imagine — and video with Vidu Q3 Turbo, PixVerse, MiniMax Hailuo, and Wan 2.6 — through one gateway key, paid in RMB.

The Access Problem, Briefly

Every major image or video model has its own gate:

• gpt-image-2 hangs off an OpenAI platform account, which needs a card most Mainland banks won't issue.
• Gemini 3 Pro Image and Gemini 3.1 Flash Image sit behind Google endpoints that are blocked or unstable from China, plus Google Cloud billing.
• Grok Imagine requires an xAI account and billing relationship most China-based teams don't have.
• The video models each come with their own console, account and top-up flow — running four of them means four integrations and four balances to watch.

Router One puts all of them behind its China-reachable gateway: one key, one wallet you can top up by card or Alipay in a single hosted checkout, and a per-request cost trace for every generation. The dedicated landing pages cover the surface area — image generation API and video generation API — this post is the hands-on walkthrough.

What's in the Catalog (August 2026 Snapshot)

Media models are unit-priced: a flat USD amount per generated image or clip, no token math. For video, the duration and resolution are fixed per model — that is what makes a flat per-clip price possible. Snapshot at time of writing — live prices are always on router.one/models:

Veo and Grok Video are not currently in the catalog — the rows above are the whole media lineup.

Setup: One Key for Everything

Create an API key in the Router One dashboard and top up — card and Alipay share one hosted checkout, and USDT/USDC works on six chains; no foreign credit card required. The same key you may already use for chat models drives the media endpoints.

export ROUTER_ONE_KEY=sk-your-router-one-key

Generating Images

The image endpoint follows the OpenAI Images API request shape — POST a model ID and a prompt:

curl -X POST https://api.router.one/v1/images/generations \
  -H "Authorization: Bearer $ROUTER_ONE_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-image-2",
       "prompt": "Flat-lay product photo of a ceramic teapot, soft morning light"}'

Because the shape is OpenAI-compatible, existing OpenAI SDK image code works after changing the base URL and key. Model choice notes from real usage:

• gpt-image-2 — strongest prompt adherence and in-image text rendering; the default for product shots and UI mockups.
• Gemini 3 Pro Image ("Nano Banana") — multimodal prompting and photorealism; strong at restyling reference images.
• Gemini 3.1 Flash Image — the Flash entry on the same Gemini line, added to the catalog in August 2026; same prompting, same flat price, worth A/B-ing against the Pro entry on your own prompts before you standardise — the Nano Banana 2 API guide has the full request shapes.
• Doubao Seedream 5.0 — the pick when your prompts are in Chinese or the output needs CJK typography.
• Grok Imagine — two catalog entries, grok-imagine-image and the higher-fidelity grok-imagine-image-quality. Both cost the same per image, so the choice is about output, not budget.

Full request and response fields are in the Images API docs.

Generating Video

Video generation is asynchronous: you submit a task, get a task ID back, and poll until the clip is ready. Don't wrap the submit call in a tight client timeout — poll instead.

# 1. Submit the task
curl -X POST https://api.router.one/v1/videos/generations \
  -H "Authorization: Bearer $ROUTER_ONE_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "viduq3-turbo",
       "prompt": "Drone shot over terraced rice fields at dawn, mist in the valleys"}'

# 2. Poll the task until it completes
curl https://api.router.one/v1/videos/generations/{task_id} \
  -H "Authorization: Bearer $ROUTER_ONE_KEY"

wan2.6-i2v is the image-to-video model: it animates a still you pass in, so it needs an image_url and rejects a prompt-only request with a 400.

curl -X POST https://api.router.one/v1/videos/generations \
  -H "Authorization: Bearer $ROUTER_ONE_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "wan2.6-i2v",
       "prompt": "Camera pushes in slowly, steam rising from the cup",
       "image_url": "https://example.com/still.jpg"}'

Generation time varies by model and load — keep the task ID and check status rather than holding a connection open. Duration and resolution are locked per model (see the table above), so a duration or size field in the body changes nothing about the clip you get; the other five models are text-to-video and reject an image_url outright. Endpoint details are in the Videos API docs.

Keeping Media Spend Under Control

Media generation is where API bills surprise people — one enthusiastic batch job is suddenly hundreds of images. The gateway's standard controls apply to media models:

• Per-request traces. Every generation lands in Dashboard → Logs with model, unit cost, and status. Finance can see exactly what a campaign's asset pipeline cost.
• Per-key budgets. Give the image pipeline its own key with a spend cap, separate from chat traffic. A runaway job stops at the cap instead of draining the wallet.
• Unit pricing. Because each image is a flat price, cost forecasting is multiplication, not token estimation.

FAQ

Is Sora available? Not currently. Today's video lineup is Vidu Q3 Turbo, PixVerse, MiniMax Hailuo 2.3 and 02, plus Wan 2.6 for image-to-video; Veo and Grok Video are not currently in the catalog either. The catalog updates as models ship; router.one/models is the source of truth.

What about Midjourney? Not in the catalog. The image lineup is gpt-image-2, Gemini 3 Pro Image, Gemini 3.1 Flash Image, Doubao Seedream, and Grok Imagine.

Is billing token-based? No — media models are unit-priced per image or per video. Chat models on the same key remain token-metered. Both appear in the same cost trace and usage dashboard.

Can one key serve chat, image, and video? Yes. That's the point of the gateway: one OpenAI-compatible key covers the chat catalog, /v1/images/generations, and /v1/videos/generations, with per-key budget controls across all of it.

How do I pay in RMB? Top up the wallet by card or Alipay on one hosted checkout — amounts convert at the checkout rate. Stablecoins (USDT/USDC on six chains) also work. See the payment walkthrough.

Conclusion

Image and video generation from China no longer requires a VPN, a foreign card, or juggling three vendor accounts. One gateway key covers gpt-image-2, Nano Banana, Seedream, and Grok Imagine for stills, and Vidu Q3 Turbo, PixVerse, MiniMax Hailuo and Wan 2.6 for clips — with flat unit pricing and a cost trace on every generation.

Start with the image generation API page for the endpoint surface, the video generation API page for video specifics, and router.one/models for live pricing.