Seedream 5.0 Lite – Flux1 AI API

Generate and edit images with Seedream 5.0 Lite. Choose 2K, 3K or 4K output, with up to 14 reference images.

POST/api/v1/generations

JSON requestAsynchronousOne image per request

6 credits per image at every quality setting. Reference images do not add an extra charge. Check credits_refunded to confirm a refund; unresolved submissions may require review.

Jump to request examples ↓

Authorization

Authorizationstringrequired

Bearer fx1_live_… — send your API key in the request header. Requires a completed paid purchase; new generations also require enough credits.

Idempotency-Keystringoptional

Use one unique value per generation and reuse it with the same body on retries. Printable ASCII, no spaces. A different body with the same key returns 409.

Maximum length: 128 characters

Manage API keys ↗

Request body

modelstringrequired

Use this exact model ID in the top-level request body.

seedream-5

promptstringrequired

Describe the image to create or the changes to apply. Whitespace is trimmed; the result must not be empty.

Maximum length: 3,000 characters

imagesstring[]optional

Publicly accessible HTTPS image URLs, up to 2,048 characters each. Omit or pass [] for text-to-image; supply references for image editing. JPEG, PNG or WebP, up to 30 MB each (provider limit). Base64 is not accepted.

Maximum items: 14

aspect_ratiostringoptional

Output width-to-height ratio. Custom dimensions and auto are not supported.

Default: 1:1

1:14:33:416:99:162:33:221:9

qualitystringoptional

basic → 2K, high → 3K, ultra → 4K. Use this field to choose the resolution tier.

Default: basic

basichighultra

output_formatstringoptional

Generated image file format.

Default: png

pngjpeg

Response & next step

A successful submission returns 202 and a generation id. Poll GET /api/v1/generations/{id} every 2–3 seconds until the status is succeeded or failed.

Read the result URL from output.images[0].url. Download it before expires_at (30 days after storage). On failure, inspect error and credits_refunded.

Generation lifecycle →Error reference →

Build your request

6 credits / image

ModeQuality

Examples only. Run on your server with your API key.

# Set FLUX1_IDEMPOTENCY_KEY once per generation; reuse it on retries.
curl --request POST 'https://flux1.ai/api/v1/generations' \
  --header "Authorization: Bearer $FLUX1_API_KEY" \
  --header 'Content-Type: application/json' \
  --header "Idempotency-Key: ${FLUX1_IDEMPOTENCY_KEY:?Set a unique key for this generation}" \
  --data '{
  "model": "seedream-5",
  "prompt": "A ceramic cup on a linen table, soft morning light",
  "aspect_ratio": "1:1",
  "quality": "basic",
  "output_format": "png"
}'

202 · POST /api/v1/generations

{
  "id": "gen_example",
  "status": "queued",
  "model": "seedream-5",
  "media_type": "image",
  "credits": 6,
  "credits_refunded": false,
  "input": {
    "prompt": "A ceramic cup on a linen table, soft morning light",
    "aspect_ratio": "1:1",
    "quality": "basic",
    "output_format": "png"
  },
  "output": null,
  "expires_at": null,
  "content_expired": false,
  "error": null,
  "created_at": "2026-09-07T08:00:00.000Z",
  "completed_at": null
}

Model notes

seedream-5 is Seedream 5.0 Lite. Seedream 5.0 Pro is a separate model and is not yet available through this API.
Choose output size with quality: basic produces 2K, high produces 3K and ultra produces 4K. Choose PNG or JPEG with output_format.
Send prompt, images, aspect_ratio, quality and output_format alongside model in the JSON body. Unknown fields are rejected, including resolution, seed, n, batch_size, custom dimensions and webhook_url.
Omitting images, or using an empty array, creates a text-to-image task. Providing 1–14 HTTPS references creates an image-editing task. Base64 input is not accepted by this model.
Content safety checking is enabled. This API produces one image per request; images counts references, not outputs.
The final image is saved to Flux storage before the generation is marked successful. A temporary status-query or storage error keeps the task queued for another attempt.