Modes and model IDs
| Mode | Model ID | Inputs & key parameters |
|---|---|---|
| Text-to-image | wan2.7-image-t2i-uncensored | prompt; Pro 1K/2K/4K or Standard 1K/2K, 1–4 images, ratios 1:1 · 16:9 · 9:16 · 4:3 · 3:4 |
| Multi-image editing | wan2.7-image-edit-uncensored | 1–9 reference images + prompt → fusion / variation; 1K/2K, 1–4 outputs |
| Inpainting | wan2.7-image-inpaint-uncensored | 1–9 images + bbox_list (≤2 boxes per image, [x1,y1,x2,y2]) + prompt |
| Grid from text | wan2.7-image-grid-t2i-uncensored | prompt → up to 12 consistent panels (character sheet / storyboard) |
| Grid from image | wan2.7-image-grid-i2i-uncensored | 1 image → up to 12 panels keeping the subject |
Every mode uses the same request shape: model + prompt + media arrays (images / videos / audios / files as public HTTPS URLs) + params. Full field tables: API docs.
Prices (USD, base list)
| Model | Variant | Price |
|---|---|---|
wan2.7-image-edit-uncensored | Pro quality | $0.08647/image |
wan2.7-image-edit-uncensored | Standard quality | $0.03387/image |
wan2.7-image-grid-i2i-uncensored | Pro quality | $0.08647/image |
wan2.7-image-grid-i2i-uncensored | Standard quality | $0.03387/image |
wan2.7-image-grid-t2i-uncensored | Pro quality | $0.08647/image |
wan2.7-image-grid-t2i-uncensored | Standard quality | $0.03387/image |
wan2.7-image-inpaint-uncensored | Pro quality | $0.08647/image |
wan2.7-image-inpaint-uncensored | Standard quality | $0.03387/image |
wan2.7-image-t2i-uncensored | Pro quality | $0.08647/image |
wan2.7-image-t2i-uncensored | Standard quality | $0.03387/image |
Base list prices from the live price list (/pricing · pricing.json); the effective price for your key is returned by GET /ent/v2/prices. Cost is reserved at submit and settled on completion — failed tasks are refunded in full.
Example request
POST https://api.18models.ai/ent/v2/generate
Authorization: Bearer sk-…
Content-Type: application/json
Idempotency-Key: <stable-request-id>
{
"model": "wan2.7-image-grid-t2i-uncensored",
"prompt": "Character sheet of a fictional woman, 6 poses, same outfit and lighting",
"params": { "resolution": "2k", "quality": "standard", "count": 6, "ratio": "1:1" }
}
The response is HTTP 202 with a task_id; poll GET https://api.18models.ai/ent/v2/tasks/{task_id} (back off 2 s → 5 s) until status is success or failed, then read result_urls. Ready-made client code: docs → Build with AI or the Agent Skill.
What is allowed
NSFW output is permitted under the 18models Content Policy: fictional adult content, including explicit sexual content, is allowed; content involving minors (in any style) or real, identifiable people is prohibited absolutely and screened on both input and output. Upstream providers apply their own checks in addition to ours — a task rejected upstream fails and is refunded automatically.
- Editing, inpainting and grid modes output 1K or 2K; 4K is text-to-image Pro only. Pick resolution + ratio from the table and the backend maps them to a legal size.
- Fictional adults only; inpainting a real person's photo into sexual content is prohibited and screened.
FAQ
Does the Wan 2.7 image API allow NSFW output?
Yes, for fictional adults, under the 18models Content Policy. Minors and real people's likenesses are prohibited and screened.
How much does Wan 2.7 image generation cost?
Standard $0.034 per image, Pro $0.086 per image — the same price at 1K, 2K and 4K. Grid generation is billed per successfully generated image.
What is Wan 2.7 grid generation?
One request returns up to 12 consistent panels — a character sheet, storyboard or expression set — from a text prompt (grid-t2i) or a reference image (grid-i2i). Storyboard panels can feed Wan 2.7 storyboard-to-video.