Krea 3 API

Generate and edit Krea 3 images from your own code. One endpoint covers both: send a prompt for text-to-image, or add up to 8 image_urls and describe the change to edit or combine them. Pick 1K or 2K, an aspect ratio or auto framing, and fast or high thinking. Providers price this model in different ways, per image or per megapixel, so the cheapest one depends on your settings; every request is priced across them and runs on the cheapest one that supports it.

$0.06per image(~60 credits)Best price

50% less than the priciest provider (3 compared). Same model, same output.

Prices last checked November 22, 2026 at 01:00 CET: Krea 3 costs from $0.025 per image on Scenetra, billed at provider cost with no markup. Each run is priced across 3 providers and runs on the cheapest one that supports your settings. Every price is re-checked against the providers daily at 01:00 CET.

1K
$0.025
2K
$0.06
2K, high thinking
$0.08
Each input image at 1K
+$0.025
Each input image at 2K
+$0.08

Quickstart

Async by design: submit a generation, get a run id back instantly, poll until it completes (or pass a callbackUrl). Each mode is its own endpoint.

Krea 3 Text to Image API

POST /api/v1/generate/krea-3Get your API key →

1 — Start a generation

curl -X POST https://app.scenetra.com/api/v1/generate/krea-3 \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"a ceramic coffee cup on a sunlit linen tablecloth, soft morning light","aspect_ratio":"16:9","resolution":"2K","thinking_mode":"fast"}'

Response (202)

{
  "runId": "run_abc123",
  "status": "PENDING",
  "model": "krea-3",
  "estimatedCredits": 60,
  "statusUrl": "/api/v1/runs/run_abc123"
}

2 — Poll until COMPLETED (every 2-5 seconds)

curl https://app.scenetra.com/api/v1/runs/run_abc123 \
  -H "Authorization: Bearer YOUR_API_KEY"

Response

{
  "runId": "run_abc123",
  "status": "COMPLETED",
  "progress": { "completed": 1, "total": 1 },
  "outputs": [
    { "type": "image", "url": "https://images.scenetra.com/..." }
  ],
  "error": null,
  "estimatedCredits": 60
}

Request fields

FieldTypeDescriptionDefault
prompt*stringDescribe the image to generate.—
aspect_ratiostringAspect ratio of the output. 'auto' lets the model pick the framing from your input images and prompt.auto · 1:1 · 4:5 · 3:4 · 2:3 · 9:16 · 5:4 · 4:3 · 3:2 · 16:9 · 21:9auto
resolutionstringOutput resolution (1K is about 1 megapixel, 2K about 4 megapixels).1K · 2K2K
thinking_modestringHow much planning happens before generation. 'fast' suits most requests; 'high' plans complex or multi-step edits more carefully, is slower and costs more.fast · highfast
callbackUrlstring (https URL)Optional. When the run finishes (completed or failed), we POST the final run status to this URL — same shape as the poll response, plus model, params, and chargedCredits. Best-effort; polling remains the source of truth.

Unknown fields are rejected with a helpful 400. Media fields take https URLs. There is no provider parameter — every run is routed to the cheapest capable provider automatically.

Good to know

Billing

Runs bill your account credits at provider cost with 0% markup. The submit response includes the credit estimate; failed generations are refunded automatically. Add ?dryRun=1 to get the estimate without running anything.

Errors

Errors are always { "error": { "code", "message" } } with stable codes: unauthorized, model_not_available, invalid_parameter, insufficient_credits, rate_limited. A failed run is not an HTTP error — poll responses report status: "FAILED" with the reason.

Krea 3 API FAQ

How do I edit an image instead of generating one?+

Add image_urls with one to eight https URLs and describe the change in prompt. The same endpoint handles both. Each input image adds to the price of the run.

What does thinking_mode change?+

fast interprets the prompt quickly and suits most requests. high plans complex or multi-step edits more carefully before generating; it takes longer and costs more per image.

Is this the official Krea API?+

No. Scenetra routes each call to a provider that serves Krea 3 (the same model and output) and bills you in Scenetra credits from one balance.

How much does the Krea 3 API cost?+

Prices last checked November 22, 2026 at 01:00 CET: Krea 3 costs from $0.025 per image on Scenetra, billed at provider cost with no markup. Each run is priced across 3 providers and runs on the cheapest one that supports your settings. Every price is re-checked against the providers daily at 01:00 CET. Rates: 1K $0.025; 2K $0.06; 2K, high thinking $0.08; Each input image at 1K +$0.025; Each input image at 2K +$0.08. With the example settings (2K), a text to image run is estimated at about 60 credits. The submit response returns the estimate for your exact settings, and adding ?dryRun=1 prices a request without running it.

Which provider runs my request?+

The cheapest one that supports your settings, chosen per request. There is no provider parameter: the same Krea 3 request is priced across every provider we route to and runs on the lowest quote.

Do failed generations cost credits?+

No. Credits are reserved when you submit and refunded automatically if the run fails. A failed run is not an HTTP error: polling returns status FAILED with the reason.

Do I have to poll, or can I get a webhook?+

Both work. Pass callbackUrl and we POST the final run status to it when the run completes or fails. Delivery is best-effort, so polling GET /api/v1/runs/{runId} remains the source of truth.