Model API

Seedream 5 Pro

ByteDance's Seedream 5.0 Pro is flagship text-to-image model, with deep-thinking prompt understanding, native text in 14 languages, and precise control over dense layouts and structured designs.

Model id

Use this in every request

bytedance/seedream/v5/pro/text-to-image

This model has other modes with their own ids: bytedance/seedream/v5/pro/edit.

Run it

Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.

# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "bytedance/seedream/v5/pro/text-to-image",
  "input": {
    "prompt": "A red ceramic cup on a wooden table, soft morning light"
  }
}'

# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"model": "bytedance/seedream/v5/pro/text-to-image", "quote_id": "QUOTE_ID", "input": {"prompt":"A red ceramic cup on a wooden table, soft morning light"}}'

# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $RAYWAKE_API_KEY"

Input

Input fields for bytedance/seedream/v5/pro/text-to-image
Name	Type	Description
`prompt`required	string	The text prompt used to generate the image.
`image_size`	object (enum)	Verified sizes: 1024² and 1536² cost one unit; 2048² costs two units. Default: `{"width":1024,"height":1024}` One of: `{"width":1024,"height":1024}`, `{"width":1536,"height":1536}`, `{"width":2048,"height":2048}`
`num_images`	number (enum)	Number of separate model generations to run with the prompt. Default: `1` One of: `1`
`output_format`	string (enum)	The file format of the generated image. Default: `jpeg` One of: `jpeg`, `png`
`watermark`	boolean	Whether to add the provider's visible watermark. Default: `false`
`sync_mode`	boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the request history. Default: `false`
`enhance_prompt_mode`	string (enum)	Prompt optimization mode. `standard` prioritizes image quality; `fast` reduces generation time. Default: `standard` One of: `standard`, `fast`

Output

A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.

Job excerpt

"outputs": [
  { "type": "image", "url": "https://…", "mime_type": "image/png", "thumbnail_url": "https://…" }
]

Pricing

1024×1024$0.11/ image
1536×1536$0.11/ image
2048×2048$0.22/ image

The exact charge for your input comes from a quote. How charges settle