> ## Documentation Index > Fetch the complete documentation index at: https://docs.laozhang.ai/llms.txt > Use this file to discover all available pages before exploring further. # Seedream 5.5 is live: transparent PNG, $0.035 > Seedream 5.5 is live on LaoZhang API: transparent PNGs from one parameter, 99-layer splits with text recognition, and what changed from 5.0. Seedream 5.5 is live on LaoZhang API from November 13, 2026, one day after BytePlus released it. A transparent product image used to take a generate step and a layer split; now one `background` parameter returns a transparent PNG for \$0.035, with any `default`-group token. * **Published**: November 13, 2026 * **Last checked**: November 13, 2026 * **Status**: Live; available in the `default` group ## Key facts | Item | Details | | - | - | | Model ID | `seedream-5-5-261028`; `dola-seedream-5-5-261028` also works, at the same price | | Released by BytePlus | November 12, 2026 | | Live on LaoZhang API | November 13, 2026 | | Endpoint | `POST /v1/images/generations`, JSON body | | Token | `default` group; Usage first or Per-call billing mode | | Price | \$0.035 per output image at any size, plus \$0.008 per reference image | | Sizes | `1K`, `1.5K`, `2K` (default), or exact pixels; no 3K or 4K | | What's new | Transparent PNG output; up to 99 layers, with a count cap and text recognition | | Account | No BytePlus account needed | ![A bookstore window at night with a cat asleep on a stack of books and a hand-lettered OPEN LATE sign, generated by Seedream 5.5](https://mintcdn.com/laozhangai-edd05f2c/HEoMLhnyMjdf-Yvq/images/samples/seedream-5-5-en-generate.jpg?fit=max\&auto=format\&n=HEoMLhnyMjdf-Yvq\&q=85\&s=6cfd5e49315c9bf7a0a0e55119f13b35) Text-to-image in the Seedream 5.5 guide: size 2K, watermark false. Returned at 2496×1664, resized for this page ![A white ceramic mug with small blue flowers on a transparent background, generated by Seedream 5.5](https://mintcdn.com/laozhangai-edd05f2c/HEoMLhnyMjdf-Yvq/images/samples/seedream-5-5-en-transparent.png?fit=max\&auto=format\&n=HEoMLhnyMjdf-Yvq\&q=85\&s=3f17d97dce5cc25f1d5710ed96d371f9) The request in Get started below: background transparent, output\_format png, size 1K. Returned as a 1024×1024 RGBA PNG ## What you can do with it | Use case | How to ask for it | Result | | - | - | - | | Product cutouts, stickers, and icons | `"background": "transparent"` with PNG output | An RGBA PNG you can place on any background, \$0.035 | | Editable posters and ads | `"layer_decomposition": true` with `text_recognition` | Background plus transparent layers; text layers include the words, font, and color | | A product in a new scene | Up to 10 images in `image` | One image built from your references; two references cost \$0.051 | | A layer split on a budget | `"max_images": 6` | At most 6 images, at most \$0.218 | ## Pricing **Seedream 5.5 costs \$0.035 per output image at 1K, 1.5K, or 2K.** * Each reference image adds \$0.008, including the first: one reference costs \$0.043 in total, two cost \$0.051, and ten cost \$0.115. * Layer decomposition is billed for every returned image, including the background. Six images from one input cost 6 × \$0.035 + \$0.008 = \$0.218. * Non-200 responses, such as parameter errors and moderation blocks, aren't charged. * A client timeout doesn't cancel a request that the server finishes. Check [call logs](https://docs.laozhang.ai/en/faq/call-logs.md) for actual charges. The full rules are in [Billing in the Seedream 5.5 guide](https://docs.laozhang.ai/en/api-capabilities/seedream-5-5.md#billing). ## Who is affected * **If you want to call Seedream 5.5**: your existing `default`-group token works. You don't need a BytePlus or Volcengine account or a new token group. * **Tokens with the Usage-based billing mode**: switch the token to Usage first or Per-call before you call this model. * **Seedream 5.0 Flash, 5.0 Pro, 5.0, 4.5, and 4.0 users**: those models keep working as before. To move to 5.5, change `model` and check the points below. Moving from 5.0 Flash or 5.0 Pro: * Remove `sequential_image_generation` and `stream`; 5.5 doesn't support them. * Expect PNG output by default. Send `"output_format": "jpeg"` if your pipeline needs JPEG. * Keep `size` at `2K` or below; 5.5 has no 3K or 4K. ## Get started **1. Prepare a token** In [Token management](https://api.laozhang.ai/token), use or create a token in the `default` group with the Usage first billing mode, then export it: ```bash theme={null} export LAOZHANG_API_KEY="YOUR_LAOZHANG_API_KEY" ``` **2. Generate a transparent PNG** ```bash theme={null} curl --fail-with-body "https://api.laozhang.ai/v1/images/generations" \ -H "Authorization: Bearer $LAOZHANG_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "seedream-5-5-261028", "prompt": "A ceramic coffee mug with small blue flowers, product shot", "background": "transparent", "output_format": "png", "size": "1K", "response_format": "url", "watermark": false }' \ -o mug.json ``` The image link is in `data[0].url`, and `data[0].background` is `transparent`. **3. Save the image** Image links are temporary, so download the file right away: ```bash theme={null} python3 -c "import json, urllib.request; urllib.request.urlretrieve(json.load(open('mug.json'))['data'][0]['url'], 'mug.png')" ``` For edits with reference images, layer decomposition, and Python examples, see the [Seedream 5.5 API guide](https://docs.laozhang.ai/en/api-capabilities/seedream-5-5.md). ## Seedream 5.5 or Seedream 5.0 All Seedream versions use the same endpoint and token, so you can switch by changing `model`. | | Seedream 5.5 | Seedream 5.0 Flash / 5.0 Pro | | - | - | - | | Transparent output | `background` on generate and edit requests | Only through layer decomposition | | Layers | Background + up to 99, a count cap, text style recognition | Background + up to 16 | | Price per image | \$0.035 | Flash \$0.018, Pro \$0.12 | | Reference images | \$0.008 each | Flash free; Pro \$0.003 each after the first | * Choose Seedream 5.5 for transparent assets, fine-grained layers, and posters whose text you want to edit. * Choose [Seedream 5.0 Flash](https://docs.laozhang.ai/en/api-capabilities/seedream-image.md) for low-cost bulk images. * Choose [Seedream 5.0, 4.5, or 4.0](https://docs.laozhang.ai/en/api-capabilities/seedream-image.md#which-seedream-version-should-i-use) for 3K or 4K output, or for several related images per request. ## FAQ ### What is the Seedream 5.5 model ID on LaoZhang API? `seedream-5-5-261028`, called through `POST /v1/images/generations`. The BytePlus name `dola-seedream-5-5-261028` also works at the same price. ### Do I need a BytePlus account to call Seedream 5.5? No. A LaoZhang API token in the `default` group is enough. Use the Usage first or Per-call billing mode. ### How much does Seedream 5.5 cost per image? \$0.035 per output image at 1K, 1.5K, or 2K, plus \$0.008 for each reference image. Layer decomposition is billed for every returned image, including the background. ### Can Seedream 5.5 make 4K images? No. The largest size is `2K`, or exact pixels up to 4,624,220 in total, such as `2048x2048`. For 3K use Seedream 5.0, and for 4K use Seedream 4.5 or 4.0. ### Can one request return several images? Only with layer decomposition, which returns a background and its layers together. Seedream 5.5 doesn't support sequential generation, so send one request per image, or use Seedream 5.0 for several related images in one request. ## Sources and related pages * [Seedream 5.5 API guide](https://docs.laozhang.ai/en/api-capabilities/seedream-5-5.md): request examples, parameters, layer fields, and billing * [Seedream API guide](https://docs.laozhang.ai/en/api-capabilities/seedream-image.md): Seedream 5.0 Flash, 5.0 Pro, 5.0, 4.5, and 4.0 * [Choose an image generation API](https://docs.laozhang.ai/en/api-capabilities/image-generation-guide.md) * [BytePlus ModelArk image generation API](https://docs.byteplus.com/en/docs/ModelArk/1541523) (checked November 13, 2026) * [BytePlus ModelArk model list](https://docs.byteplus.com/en/docs/modelark/model-list) (checked November 13, 2026) * [Models and pricing](https://docs.laozhang.ai/en/models.md) * [LaoZhang API announcements](https://docs.laozhang.ai/en/changelog.md) This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.