Recraft AI 20b delivers affordable, fast image generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
就绪

$0.022每次运行·~45 / $1

Cyberpunk girl with neon pink hair and glowing implants walking through rainy Tokyo streets, reflections, neon signs, 4K hyper-detail, Blade Runner vibes

A young woman in a white blouse and denim skirt standing in a sunlit kitchen, soft morning light

Old man with a long grey beard reading a book under a streetlamp at night, cinematic lighting, photorealistic, vintage atmosphere, 85mm lens

Android boy sitting in a futuristic subway, LED lights flickering, chrome skin, dystopian mood, cyberpunk fashion

Baroque painting of a knight in ornate armor holding a rose, dark velvet backdrop, Rembrandt lighting, regal expression

Woman with a galaxy for hair, floating in space surrounded by glowing jellyfish, surreal dreamscape, vivid colors, concept art

Modern African woman in bold patterned Ankara dress, standing in a desert with a sunset backdrop, fashion editorial style, rich textures

Street style portrait of a Gen Z fashion influencer in oversized jacket and sneakers, urban background, natural light, detailed facial expression and accessories

High fashion model posing in a minimalist studio, dramatic shadow play, sharp cheekbones, avant-garde makeup, Vogue editorial style, high resolution

An astronaut floats weightlessly outside a space station, Earth spinning slowly below, camera rotates to create a dizzying zero-gravity effect, ambient sci-fi tone
Recraft 20B is a large-scale text-to-image model that “thinks in design language.” It is tuned for layouts, typography, brand-safe compositions, and clean text rendering, making it ideal for social graphics, ads, presentations, and product visuals where design quality matters as much as realism.
Design-first image generation Strong understanding of layout, hierarchy, and composition for poster-style images, thumbnails, and marketing assets.
Sharp, readable text on images Generates high-quality embedded text—from short labels to longer headlines—directly inside the image.
Rich style system Curated style presets (for example, igital_illustration/grain make it easy to switch between illustration, painterly, and graphic styles without rewriting prompts.
Brand and identity friendly Handles logos, icons, and UI-like designs with improved anatomy, alignment, and visual consistency.
Vector-aware design Originates from a system that supports both raster and vector workflows, making it particularly strong for flat design, icons, and graphic illustration.
Outputs are delivered as high-quality raster images suitable for web, slides, and print-oriented workflows.
Simple per-image billing:
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/recraft-ai/recraft-20b with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Recraft 20b below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"style": "realistic_image/b_and_w"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/recraft-ai/recraft-20b" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/recraft-ai/recraft-20b";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"style": "realistic_image/b_and_w"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"style": "realistic_image/b_and_w"
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/recraft-ai/recraft-20b", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)Recraft 20b is a Recraft model for image generation, exposed as a REST API on WaveSpeedAI. Recraft AI 20b delivers affordable, fast image generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/recraft-ai/recraft-ai-recraft-20b.
Recraft 20b starts at $0.022 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `aspect_ratio`, `enable_base64_output`, `style`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/recraft-ai/recraft-ai-recraft-20b.
Median end-to-end generation time on WaveSpeedAI is around 7 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (Recraft). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.