Image & Video Generation APIs from China: gpt-image-2, Nano Banana & Veo

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 July 2026: generating images with gpt-image-2, Gemini 3 Pro Image (the model line the community searches as "Nano Banana"), Doubao Seedream, and Grok Imagine — and video with Veo 3.1 and Grok Video — 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 Veo sit behind Google endpoints that are blocked or unstable from China, plus Google Cloud billing.
• Grok's media models require an account and billing relationship most China-based teams don't have.

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

What's in the Catalog (July 2026 Snapshot)

Media models are unit-priced: a flat USD amount per generated image or clip, no token math. Snapshot at time of writing — live prices are always on router.one/models:

Setup: One Key for Everything

Create an API key in the Router One dashboard and top up — WeChat Pay, Alipay, Stripe, and USDT/USDC on six networks all work; 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.
• Doubao Seedream 5.0 — the pick when your prompts are in Chinese or the output needs CJK typography.
• Grok Imagine lite / standard / pro — three price-quality points on one family; lite is fine for thumbnails and drafts.

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": "veo3.1-fast",
       "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"

Generation time varies by model and load — keep the task ID and check status rather than holding a connection open. Grok Video comes in fixed 10-second and 15-second durations; Veo 3.1 has a speed-first tier and 4K components variants. 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 — the video lineup today is Veo 3.1 and Grok Video. 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, 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 with Alipay or WeChat Pay — amounts convert at the checkout rate. Stablecoins (USDT/USDC on six networks) and Stripe 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, Grok Imagine, Veo 3.1, and Grok Video — with flat unit pricing and a cost trace on every generation.

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