Generate and edit 1K, 1.5K or 2K images at one per-image rate, with up to 10 reference inputs at no extra cost. Use Flash Layerize to split one image into a base image and up to 16 PNG layers.
Test Seedream 5.0 Flash speed and output quality, estimate credit usage, and generate a sample before you formally integrate.
Create image task
Fixed to doubao-seedream-5.0-flashText-to-image, image-to-image and editing. One image per request, same price at 1K, 1.5K and 2K.
Upload source or reference images. Input images are not billed.
Transparent needs exactly one input image that already has an alpha channel.
Generated images will appear here.
Results are kept for 24 hours — download anything you want to keep.
One flat rate per image at 1K, 1.5K or 2K, and reference images are free. Pick a testing budget, or expand for detailed rates.
First Test Cost
Seedream 5.0 Flash - Text-to-Image - 1K - 1 imageOne image at any quality tier
About 617 tests with $10 in credits.
In Playground, keep Seedream 5.0 Flash selected and generate one image. 1K, 1.5K and 2K cost the same and reference images are free, so you can test at full 2K quality from the first run.
Seedream 5.0 Flash testing budget guide
Pick an amount based on how many tests you expect.Good for a first validation.
Good for prompt iteration.
Good before production integration.
One flat rate per output image — 1K, 1.5K and 2K cost the same, and reference images are free.
doubao-seedream-5.0-flash| Item | Rule | Rate | Billing |
|---|---|---|---|
| 1K / 1.5K / 2K output | Each generated image. All three quality tiers cost the same, so 2K costs no more than 1K. | $0.017/image-10% 1.1016 cr/image$0.018 official price | Output image |
doubao-seedream-5.0-flash-layerize| Item | Rule | Rate | Billing |
|---|---|---|---|
| Each output image | The base image and every split layer are billed as one image each. A run yields one base image plus up to 16 layers. | $0.017/image-10% 1.1016 cr/image$0.018 official price | Output image |
| Item | Rule | Rate | Billing |
|---|---|---|---|
| Reference images | Images in image_urls for image-to-image and editing, up to 10 per request. | Free | Not billed |
| Layer Split reserve | Up to 17 images (1 base + 16 layers) are reserved when the task starts. You pay only for the images actually produced; the rest is refunded. | 1.1016 cr/image | Refunded after completion |
Use Seedream 5.0 Flash for ad iterations, product-image edits and multi-reference compositions. Ordinary generation returns one image; Layerize returns a base image and separate transparent layers. Compare output quality on your own prompts before choosing a production workflow.
doubao-seedream-5.0-flashGenerate or edit a flat image from a prompt, with up to 10 reference images, ratio presets or custom pixel sizes, and 1K/1.5K/2K quality tiers at one price.
doubao-seedream-5.0-flash-layerizeSend exactly one PNG or JPEG and get a base image plus up to 16 transparent PNG layers with stacking order and bounding boxes, billed per image produced.
These fields cover the main integration decisions. Open the API tab for the full request and response schema.
modelstringdoubao-seedream-5.0-flash for generation and editing; doubao-seedream-5.0-flash-layerize for Layer Split.
promptstringDescribe the image. Up to 4000 tokens; under about 600 English words works best.
image_urlsarrayUp to 10 reference images for image-to-image or editing. Reference images are free.
sizestringauto, an aspect ratio such as 1:1 or 16:9, or custom WIDTHxHEIGHT pixels.
qualityenum1K, 1.5K or 2K for auto or ratio sizes. All three tiers cost the same.
output_formatenumjpeg or png. Transparent backgrounds require png.
backgroundenumUse transparent only to preserve the alpha channel of exactly one input image, with PNG output. It does not remove a background.
callback_urlstringHTTPS webhook that receives the task result instead of polling.
Use the EvoLink API for product integration and batch jobs, or call it from Codex, Claude, or Gemini for fast creative and development workflows. Both paths share the same EvoLink API key, balance, model routes, and task history.
Best for: product backends, batch jobs, automated workflows
Call EvoLink’s unified image API from your server and control the model ID, parameters, task queue, callbacks, and result storage.
Best for: creative and development tasks in Codex, Claude, and Gemini
Give the Agent your output goal, assets, and acceptance criteria. It can choose the route, assemble the request, track the task, and return the result without requiring you to hand-code every step.
This example shows the shortest runnable flow: create a task, save the returned task ID, then poll or wait for an HTTPS callback. Open the API tab for the complete parameter and response reference.
curl -X POST https://api.evolink.ai/v1/images/generations \
-H "Authorization: Bearer $EVOLINK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seedream-5.0-flash",
"prompt": "A serene lake reflecting the sunset, editorial photography",
"size": "16:9",
"quality": "2K",
"output_format": "jpeg",
"callback_url": "https://your-domain.com/webhooks/image-task-completed"
}'
# Save the returned task ID, then query:
curl https://api.evolink.ai/v1/tasks/{task_id} \
-H "Authorization: Bearer $EVOLINK_API_KEY"Check every value against the parameter cards above: ranges, allowed options, asset counts, and file types must match the selected route.
Check the Authorization bearer token and confirm the available balance and task billing in the console.
Review likeness rights, brand assets, readable text, sensitive content, and input-asset compliance.
A Seedream 5.0 Flash task that reaches a final failed state is not charged. Keep the task ID, inspect the final state, and identify whether the cause is validation, review, or execution before retrying.
callback_url must be a public HTTPS URL, not localhost or a private network address. Always keep the task ID as a polling fallback.
| Feature | Seedream 5.0 Flash | Nano Banana | GPT Image |
|---|---|---|---|
| Starting price | ~$0.017 / image | See selected model | Token or tier based |
| Output quality | 1K / 1.5K / 2K, same price | 1K / 2K / 4K by model | Quality tiers |
| Reference input | Up to 10 images, free | Model dependent | Supported |
| Layer output | Base + up to 16 PNG layers | No native layer output | No native layer output |
| Best for | Fast, high-volume image workflows | High-quality image generation | OpenAI image workflows |
Output tier, reference images and prompt length do not change the price - you pay per image produced.
A Layer Split run returns one base image plus up to 16 layers, each billed as one image. Up to 17 images are reserved upfront and the unused part is refunded.
Flash accepts prompt_priority: standard only. A Pro request using fast must be updated before switching the model ID; review each route's pricing and input limits too.
See the flat per-image rate and your estimate before you add credits.
One API key works across Seedream, Nano Banana, GPT Image, video, audio, and LLM models.
Track credits, spending, and model usage in one console.
See whether an image task is submitted, processing, completed, or failed.
Test drafts, edits, and layer splits on one page before you integrate.
Compare output limits, reference handling, prompt modes and billing across Seedream models under one EvoLink account and API key.
Seedream 5.0 Pro
Compare Pro for its standard and fast prompt modes, resolution-based pricing and Layerize workflow. Evaluate output quality using the same prompts and references.
View API
Seedream 5.0 Lite
Evaluate Lite when your workflow needs web-search-enhanced generation. Check its own resolution, reference limits and optional search charges.
View API
Seedream 4.5
Previous Seedream image route for teams that need 2K/4K generation, multi-image editing, and established production behavior.
View API
GPT Image 2.5 Flare
OpenAI's default GPT Image 2.5 route for fast, high-quality everyday generation, billed by tokens.
View API
GPT Image 2.5 Sunburst
GPT Image 2.5 variant tuned for editing precision, trading longer generation times for finer detail control.
View API
Grok Imagine Image 2.0
xAI image model for text-to-image and editing with 1–3 reference images, with 1K/2K output.
View APISeedream 5.0 Flash is ByteDance's image generation and editing model for latency- and cost-sensitive workflows. On EvoLink, use doubao-seedream-5.0-flash for ordinary generation or editing, and doubao-seedream-5.0-flash-layerize for layer decomposition. The two models share this page but have different input and output rules.
They are separate models. doubao-seedream-5.0-flash generates or edits a flat image and accepts ratios and custom pixel sizes. doubao-seedream-5.0-flash-layerize takes exactly one PNG or JPEG, accepts quality tiers only, and returns a base image plus up to 16 transparent PNG layers with stacking order and bounding boxes.
Check the pricing section for the current EvoLink rate. Ordinary generation uses one flat output-image rate at 1K, 1.5K and 2K; image_urls inputs are not billed. Layerize has its own rate entry and bills the base image plus every generated layer, not one flat charge for the entire task.
The number of layers is unknown when the task starts, so up to 17 images are reserved. You pay only for the images actually produced, and the rest returns to your balance.
No. Flash accepts prompt_priority: standard only; fast is rejected before billing. When migrating a Pro request, remove fast and compare your own turnaround time rather than assuming a fixed generation speed.
Yes. Use the Playground to test output quality, estimate credits, and inspect the request JSON before wiring it into your product.
Not yet. Seedream 5.0 Flash returns one image per request.
Yes. Pass image_urls with the prompt when you want source images or references to guide an edit or image-to-image workflow.
Failed tasks are not billed. Check the task status and error details in the response or console, adjust the request, and try again.
Use an EvoLink API key to POST /v1/images/generations with the Flash model ID and the fields shown in this page's API reference. Save the returned id and query /v1/tasks/{task_id}, or provide an HTTPS callback_url. The create response is a task record, not the finished image.
Evaluate Flash for flat-rate 1K–2K generation, reference-guided edits and Layerize. Pro offers standard and fast prompt modes with different billing rules. Lite supports a different feature set, including web-search-enhanced generation. Compare the family page, then test the same prompts; price and tier names do not prove a quality ranking.
background: transparent preserves an existing alpha channel from exactly one input image. Use an alpha-capable source and PNG output; JPEG output is rejected. This option is not a background-removal tool. For independent transparent elements from a finished image, use Flash Layerize.
Flash supports 1K, 1.5K and 2K output tiers, not a 4K tier. For ordinary generation, size can be auto, an aspect ratio or WIDTHxHEIGHT within the documented pixel and ratio limits. Layerize uses quality: auto, 1K, 1.5K or 2K and does not accept aspect ratios or custom pixel sizes.