wan-2-7-image

Quick example

curl https://reapi.ai/api/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-image-pro",
    "prompt": "a flower shop with delicate windows and a beautiful wooden door, blossoms out front",
    "size": "16:9",
    "resolution": "2K",
    "n": 1
  }'

import requests

resp = requests.post(
    "https://reapi.ai/api/v1/images/generations",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "wan2.7-image-pro",
        "prompt": "a flower shop with delicate windows and a beautiful wooden door, blossoms out front",
        "size": "16:9",
        "resolution": "2K",
        "n": 1,
    },
    timeout=30,
)
print(resp.json())

const r = await fetch("https://reapi.ai/api/v1/images/generations", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "wan2.7-image-pro",
    prompt: "a flower shop with delicate windows and a beautiful wooden door, blossoms out front",
    size: "16:9",
    resolution: "2K",
    n: 1,
  }),
});
console.log(await r.json());

package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "io"
    "net/http"
)

func main() {
    body, _ := json.Marshal(map[string]any{
        "model":      "wan2.7-image-pro",
        "prompt":     "a flower shop with delicate windows and a beautiful wooden door, blossoms out front",
        "size":       "16:9",
        "resolution": "2K",
        "n":          1,
    })
    req, _ := http.NewRequest("POST",
        "https://reapi.ai/api/v1/images/generations", bytes.NewReader(body))
    req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
    req.Header.Set("Content-Type", "application/json")

    resp, _ := http.DefaultClient.Do(req)
    defer resp.Body.Close()
    out, _ := io.ReadAll(resp.Body)
    fmt.Println(string(out))
}

Submit response

{
  "id": "task_018f5a3a1b6e7d9f8c2b4d6e8f0a2c4e",
  "model": "wan2.7-image-pro",
  "status": "processing",
  "created_at": 1735000000
}

Poll GET /api/v1/tasks/{id} (see the Tasks reference) until status === "completed". The completed payload's output.image_urls holds the generated image URLs.

Authentication

Every call needs a Bearer token. Generate keys at reapi.ai/settings/apikeys.

Authorization: Bearer YOUR_API_KEY

Endpoint

POST /api/v1/images/generations
GET  /api/v1/tasks/{id}

Submission is async. The POST returns immediately with a task_id; the task endpoint returns the same envelope until completion. Polling does not consume credits.

Tiers

Two model ids share one parameter shape:

Pick Pro for hero / print-grade detail and 4K; Standard for fast everyday work.

Modes

There is no mode field — the mode is implicit in the request shape:

• Text-to-image — no image_urls. prompt is required.
• Editing / multi-image reference — pass image_urls. prompt is optional (recommended). The output aspect ratio follows the last input image.
• Interactive region editing — add bbox_list to target exact regions.
• Group series — set enable_sequential: true for a consistent connected set; raises the n cap to 12.

Request body

model — string, required

One of wan2.7-image or wan2.7-image-pro.

prompt — string

Up to 5,000 characters. Required for text-to-image (no image_urls); optional but recommended in editing mode.

image_urls — array, optional

Reference images for editing / multi-image fusion. Public HTTPS URLs only — base64 / data: URIs are rejected at the gateway. Up to 9 images. Passing any image switches the request to editing mode.

n — integer, default 1

Images per call. Range [1, 4] normally; up to [1, 12] when enable_sequential is true. Billed per generated image.

size — string

Output sizing. Polymorphic per the model:

• a gear keyword — 1K / 2K / 4K
• an aspect ratio — 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3
• a pixel value — 1024x1024

Pair an aspect ratio here with the quality gear in resolution.

resolution — string

Quality gear: 1K / 2K / 4K (case-insensitive).

negative_prompt — string, optional

What to keep out of the image, e.g. "blurry, distorted, low quality".

watermark — boolean, default false

Set true to add an AI-generated watermark to the bottom-right corner.

seed — integer, optional

Range [0, 2147483647]. The same seed with the same parameters yields a similar, stable result.

thinking_mode — boolean, default true

Enables extra reasoning for higher image quality. Only effective for text-to-image with no reference image and outside group mode; ignored otherwise.

enable_sequential — boolean, default false

Turns on group mode — a consistent, connected series in one call. Raises the n cap to 12. In group mode thinking_mode and color_palette do not apply.

bbox_list — array, optional

Interactive-edit regions. A list parallel to image_urls — one entry per input image — where each entry is a list of up to two boxes, and each box is [x1, y1, x2, y2] in absolute pixels with origin at the top-left. Use [] for an image you are not boxing.

{
  "image_urls": [
    "https://example.com/clock.webp",
    "https://example.com/desk.webp"
  ],
  "bbox_list": [
    [],
    [[989, 515, 1138, 681]]
  ]
}

color_palette — array, optional

Steer the image toward a custom palette. 3-10 items of { hex, ratio } where ratio is a percentage string and all ratios sum to 100.00%. Non-group mode only.

{
  "color_palette": [
    { "hex": "#C2D1E6", "ratio": "23.51%" },
    { "hex": "#636574", "ratio": "76.49%" }
  ]
}

Pricing

Wan 2.7 Image bills a flat rate per successfully generated image, independent of resolution and aspect ratio. Total charge is the per-image rate times n:

credits = ceil(per_image_usd × n × 1000)

where 1 credit = $0.001 USD. The Pro tier carries a higher per-image rate than Standard. Failed and rejected requests are not charged.

The exact per-image credit cost for each tier surfaces on the model page and through the playground estimator before submit.

Response

The poll envelope returns image URLs in output.image_urls:

{
  "id": "task_019dfd44b7fd74168541552a3260a623",
  "model": "wan2.7-image-pro",
  "status": "completed",
  "output": {
    "image_urls": [
      "https://cdn.reapi.ai/...png"
    ]
  }
}

For a group-mode request (enable_sequential: true, n > 1), image_urls holds the full series in order. Mirror the URLs to your own storage if you need long-term retention.

Errors

Failures return the standard reAPI envelope { error: { code, message, request_id } }. Common cases:

• Invalid input (out-of-range n, 4K requested in edit/group mode, a bbox_list whose length does not match image_urls, a non-HTTPS media URL) → 400.
• Insufficient credits → 402.
• Rate limited → 429.

See the full catalog at /docs/api/errors.

Tips

• The mode is decided by your inputs, not a flag — omit image_urls for pure generation, include it to edit.
• For precise edits, prefer bbox_list over describing the location in the prompt — boxed regions composite with matched lighting and perspective.
• For storyboards and comic panels, use group mode (enable_sequential: true) so the series stays on-model in one call instead of stitching separate requests.
• Reach for wan2.7-image-pro at resolution: "4K" (text-to-image) when the asset goes to print or a retina display; use wan2.7-image for fast drafts.

Related

• Image generation models
• Seedream 5.0 Lite
• Tasks API
• Error codes