recraft-ai/recraft-v3

POST

/ws/api/v3/recraft-ai/recraft-v3

Recraft V3 (codenamed red_panda) is a text-to-image model capable of generating long texts and images in various styles. As of now, it is at the SOTA level in the field of image generation, as demonstrated by the text-to-image benchmark tests from Artificial Analysis.

Request

Header Params

Body Params application/json

Example

{
  "aspect_ratio": "3:4",
  "enable_base64_output": false,
  "prompt": "Ultra-realistic portrait of a young woman with windswept hair, wearing a leather jacket, golden hour lighting, 85mm lens, cinematic color grading, visible skin texture and pores",
  "style": "realistic_image"
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.302.ai/ws/api/v3/recraft-ai/recraft-v3' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data-raw '{
  "aspect_ratio": "3:4",
  "enable_base64_output": false,
  "prompt": "Ultra-realistic portrait of a young woman with windswept hair, wearing a leather jacket, golden hour lighting, 85mm lens, cinematic color grading, visible skin texture and pores",
  "style": "realistic_image"
}'

Responses

🟢200成功

application/json

Body

Example

{
    "code": 200,
    "message": "success",
    "data": {
        "id": "51aefa20d0ae459ab6689e8694106785",
        "model": "wavespeed-ai/flux-dev-ultra-fast",
        "outputs": [],
        "urls": {
            "get": "https://api.302.ai/ws/api/v3/predictions/51aefa20d0ae459ab6689e8694106785/result"
        },
        "has_nsfw_contents": [],
        "status": "created",
        "created_at": "2025-10-20T08:26:46.871Z",
        "error": "",
        "executionTime": 0,
        "timings": {
            "inference": 0
        }
    }
}

Modified at 2025-10-27 10:50:57

reve/text-to-image

recraft-ai/recraft-v3-svg