Skip to main content
POST
cURL

Authorizations

Authorization
string
header
required

Use your APIPod API key as a Bearer token in the Authorization header.

Body

application/json
model
string
required

Public APIPod model ID.

Allowed value: "qwen-image-3.0"
prompt
string
required

What to generate, or how to edit the reference images when image_urls is present. Prompts up to about 4.5k tokens are accepted.

Maximum string length: 32000
aspect_ratio
enum<string>

Output aspect ratio, used together with resolution. Any ratio from 1:8 to 8:1 is accepted.

Available options:
auto,
1:1,
1:2,
2:1,
1:3,
3:1,
1:4,
4:1,
1:8,
8:1,
2:3,
3:2,
3:4,
4:3,
4:5,
5:4,
9:16,
16:9,
9:21,
21:9
enable_thinking
boolean

Enable reasoning before rendering to improve output quality at the cost of latency. Takes effect only when prompt_extend is enabled; the upstream default is on.

image_urls
string[]

Optional. Omit for text-to-image; pass 1 to 3 images to switch the same model into instruction-based editing.

n
enum<integer>
default:1

Number of images to generate per request. Each returned image is billed separately.

Available options:
1,
2,
3,
4,
5,
6
Required range: 1 <= x <= 6
prompt_extend
boolean
default:true

Expand short prompts before rendering (adds 3 to 5 seconds). Disable for precise, already-detailed prompts.

prompt_extend_mode
enum<string>

Prompt rewriting strategy when prompt_extend is enabled. direct (the default) supports both text-to-image and editing; agent rewrites in more detail and is supported for text-to-image only.

Available options:
direct,
agent
resolution
enum<string>
default:2K

Recommended output tier. Combined with aspect_ratio the API derives the exact pixel size. Requests without size are billed at the 2K tier.

Available options:
1K,
2K
seed
integer

Random seed from 0 to 2147483647. Reuse a seed for more stable results.

Required range: 0 <= x <= 2147483647
size
string

Exact pixel override, WIDTHxHEIGHT. Total pixels must stay between 512512 and 20482048 at 1:8 to 8:1. Takes precedence over resolution and aspect_ratio; omit to let the model choose.

watermark
boolean
default:false

Add an AI-generated watermark in the bottom right corner.

Response

200 - application/json

Task accepted

Standard response for task submission

code
integer
required
data
Task Submit Data · object
required

Data content for task submission

message
string
required