Cookie Preferences
We use cookies to personalize content and analyze traffic. See our Cookie Policy.
No image yet. Submit the form to generate image.
Explore different use cases and parameter configurations
Transparent pricing with no hidden fees. Pay as you go.
The price is independent of image resolution and is solely determined by the final number of images returned. The number of images depends on the quantity specified in the prompt and the maximum value set by max_images, both of which jointly determine the final count.
| Rule & Modality | Channel | Credits | Price (USD) | Official / Reference Price | Daily Savings |
|---|---|---|---|---|---|
seedream-v4-max_image_1 imageseedreammax_images: 1 | Starter | 0.6per run | $0.003 | Bytedance$0.030per run | Based on 10,000 images/dayBytedance costs $272.730/day moreApiPass is 90.91% lower |
seedream-v4-max_image_2 imageseedreammax_images: 2 | Starter | 1per run | $0.005 | Bytedance$0.060per run | Based on 10,000 images/dayBytedance costs $554.550/day moreApiPass is 92.42% lower |
seedream-v4-max_image_3 imageseedreammax_images: 3 | Starter | 1per run | $0.005 | Bytedance$0.090per run | Based on 10,000 images/dayBytedance costs $854.550/day moreApiPass is 94.95% lower |
seedream-v4-max_image_4 imageseedreammax_images: 4 | Starter | 1per run | $0.005 | Bytedance$0.120per run | Based on 10,000 images/dayBytedance costs $1154.550/day moreApiPass is 96.21% lower |
seedream-v4-max_image_5 imageseedreammax_images: 5 | Starter | 1per run | $0.005 | Bytedance$0.150per run | Based on 10,000 images/dayBytedance costs $1454.550/day moreApiPass is 96.97% lower |
seedream-v4-max_image_6 imageseedreammax_images: 6 | Starter | 1per run | $0.005 | Bytedance$0.180per run | Based on 10,000 images/dayBytedance costs $1754.550/day moreApiPass is 97.47% lower |
Competitor pricing costs $272.730/day more
ApiPass is 90.91% lower, estimated at Based on 10,000 images/day
seedream-v4-max_image_1
max_images: 1
ApiPass Price
$0.003
0.6 credits per run
Competitor Prices
Complete guide to using seedream-4
Build with ByteDance Seedream V4 on ApiPass using one public model name: bytedance/seedream-v4. The API supports text-to-image generation, image-to-image editing, reference consistency, batch outputs, and high-definition results through an asynchronous Jobs workflow.
Seedream 4.0 is ByteDance's next-generation image creation model for fast visual generation and precise editing. It combines text-to-image, image-to-image, and instruction-based editing in a unified architecture, helping developers generate polished visuals, preserve reference details, and create consistent outputs across creative and professional workflows. On ApiPass, the same public model name is used for both generation and editing: omit input.image_urls or pass an empty array for text-to-image, or provide one or more image URLs for editing.
Generate high-quality images from natural language prompts. Seedream 4.0 supports complex scenes, product visuals, illustrations, and marketing assets with selectable image sizes and 1K, 2K, or 4K output scale.
Provide one or more reference images and describe the transformation you want. ApiPass automatically routes requests with non-empty input.image_urls to the editing workflow while preserving the public model name bytedance/seedream-v4.
Use natural language to add, remove, replace, restyle, or refine objects, backgrounds, colors, and composition. Editing mode supports up to 10 public JPEG, PNG, or WebP input images, each up to 30 MB.
Seedream 4.0 can follow simple natural language instructions to add, remove, or replace visual elements. This makes it useful for commercial design, creative edits, background changes, and controlled image refinement.
The model is designed to maintain identity, composition, and fine details across style changes, helping outputs keep the source subject recognizable while avoiding an over-processed look.
Seedream 4.0 interprets detailed or abstract prompts, adapts composition and proportions, and turns creative intent into concrete visuals for product, design, and storytelling workflows.
Editing mode accepts up to 10 input images, and max_images can request up to 6 generated outputs in one task. For multi-output tasks, describe the exact desired count in the prompt as well as setting max_images.
Seedream 4.0 supports 1K, 2K, and 4K output scales. Final pixel dimensions are controlled by image_size and image_resolution, such as landscape_4_3 with 4K for a 4096 x 3072-style output scale.
Turn rough ideas into polished drafts, illustrations, product concepts, and 3D-style prototypes while preserving style and visual detail across iterations.
Create ads, banners, product visuals, campaign images, and social-ready creative assets quickly with consistent brand styling and controllable output sizes.
Generate scene concepts, storyboard frames, character variations, and visual directions for pre-production workflows where fast iteration and coherent composition matter.
Power AI-generated selfies, creative memes, character swaps, playful edits, and interactive visual experiences using text prompts and optional reference images.
ApiPass exposes one public model name for both text-to-image and editing workflows, then selects the correct upstream branch from input.image_urls.
Use model bytedance/seedream-v4 and omit input.image_urls, or provide image_urls as an empty array. ApiPass routes the task to text-to-image generation and returns generated images through the asynchronous task result.
Provide input.image_urls with at least one non-empty public image URL. ApiPass routes the task to image editing. The public model name, billing, catalog entry, and API integration remain bytedance/seedream-v4.
Create a task with POST /api/v1/jobs/createTask, save data.taskId, then poll GET /api/v1/jobs/recordInfo or provide a root-level callBackUrl. On success, read generated image URLs from resultJson.resultUrls.
For the regular channel, credits are pre-deducted based on the requested max_images value at 11 credits per image. Billing uses the requested maximum output count, not the final number of returned URLs.
max_images must be a JSON integer from 1 to 6. A request for 1 image pre-deducts 11 credits on the regular channel, while a request for 6 images pre-deducts 66 credits.
Actual online pricing follows the current ApiPass model configuration, selected channel, and account settlement results. The default channel is auto, which allocates tasks based on available provider pricing and stability.
Write a non-empty prompt up to 5000 characters. For text-to-image, leave image_urls empty. For editing, provide 1 to 10 publicly accessible JPEG, PNG, or WebP image URLs, each up to 30 MB.
Send POST /api/v1/jobs/createTask with model set to bytedance/seedream-v4 and your input object. You can set image_size, image_resolution, max_images, and seed. Keep callBackUrl at the root level if you want completion callbacks.
Save data.taskId from the create response. Poll GET /api/v1/jobs/recordInfo?taskId=... until the state is success or fail, or handle the terminal callback payload. On success, parse resultJson and read resultUrls.
All APIs require authentication via Bearer Token.
Authorization: Bearer
Create an asynchronous ByteDance Seedream V4 image generation or image editing task. ApiPass uses the same public model name for both modes and automatically selects the upstream workflow from input.image_urls.
The API accepts a JSON payload with the following structure:
1{
2 "model": "bytedance/seedream-v4",
3 "callBackUrl": "string (optional)",
4 "channel": "auto",
5 "input": {
6 "prompt": "string",
7 "image_urls": ["string"],
8 "image_size": "square_hd",
9 "image_resolution": "1K",
10 "max_images": 1,
11 "seed": 42
12 }
13}modelRequiredstringThe public ApiPass model name. Use bytedance/seedream-v4 for both text-to-image and image editing tasks.
"bytedance/seedream-v4"
callBackUrlOptionalstringOptional callback URL for receiving task completion notifications from ApiPass. Do not put this field inside input.
"https://your-domain.com/api/callback"
channelOptionalstringSelects the provider channel used by APIPASS for the actual image generation or editing task. The default channel is auto. APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics. starter is ultra-low-cost with limited quotas and weaker stability. regular is standard and much cheaper than official APIs with moderate stability. official uses the model native API with high stability, fast task execution, and official pricing.
The default value for the channel parameter is auto. APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics. Use starter for ultra-low-cost tasks with limited quotas and weaker stability, regular for standard lower-cost routing with moderate stability, and official for the model native API with high stability, fast task execution, and official pricing.
Available options:
auto
The input object contains the Seedream V4 generation and editing parameters.
input.promptRequiredstringImage generation or editing prompt. Must be a non-empty string up to 5000 characters.
Required. Maximum length: 5000 characters.
input.image_urlsOptionalstring[]Input image URLs for image editing. If omitted or an empty array, ApiPass uses text-to-image mode. If the array contains at least one non-empty URL, ApiPass uses image editing mode.
Default: []. Supports up to 10 images. Each image must be a publicly accessible JPEG, PNG, or WebP file up to 30 MB.
["https://cdn.example.com/product.png"]
input.image_sizeOptionalenum: ['square', 'square_hd', 'portrait_4_3', 'portrait_3_2', 'portrait_16_9', 'landscape_4_3', 'landscape_3_2', 'landscape_16_9', 'landscape_21_9']Output image size and aspect ratio.
Default: square_hd. Final pixel dimensions are determined by image_size together with image_resolution.
Available options:
"square_hd"
input.image_resolutionOptionalenum: ['1K', '2K', '4K']Output pixel scale. The value is case-sensitive.
Default: 1K. Use exactly 1K, 2K, or 4K.
Available options:
"1K"
input.max_imagesOptionalintegerMaximum number of images to generate for the task.
Default: 1. Range: 1 to 6. Must be a JSON integer, not a string, decimal, or boolean.
1
input.seedOptionalnumberRandom seed used to control generation randomness. Integers and floating-point numbers are accepted.
Default: random. Strings and booleans are not valid.
42
1curl --request POST \
2 --url "https://api.apipass.dev/api/v1/jobs/createTask" \
3 --header "Authorization: Bearer YOUR_API_KEY" \
4 --header "Content-Type: application/json" \
5 --data '{
6 "model": "bytedance/seedream-v4",
7 "channel": "auto",
8 "input": {
9 "prompt": "A premium outdoor product collection in a bright modern studio.",
10 "image_size": "square_hd",
11 "image_resolution": "1K",
12 "max_images": 1
13 }
14 }'1{
2 "code": 200,
3 "message": "success",
4 "data": {
5 "taskId": "task_xxxxxxxxxxxxxxxx"
6 }
7}codeStatus code, 200 indicates that the task was created successfully.
messageResponse message.
data.taskIdApiPass task ID. Save this value and use it with the Query Task API to retrieve task status and results.
flux
flux
Generate photorealistic images with robust text
Starting from
0 credits
Nano Banana 2 Lite, aka Gemini 3.1 Flash-Lite Image, is a newly released image model from Google DeepMind built for fast 1K image generation, efficient creative iteration, prompt-based image editing, and responsive visual output in product-facing creative scenarios.
Starting from
0 credits
OpenAI
OpenAI
Generate intentionally designed visuals with less prompting using the latest OpenAI GPT Image 2 model.
Starting from
0 credits
Qwen
Qwen
Starting from
0 credits
Nano Banana now allows you to freely draw on edited images, bringing you a completely new experience. Simply click on the image to draw whatever you want. You can also add text and details, and Gemini will do the rest.
Starting from
0 credits
Fast image generation model built on Gemini 3.1 Flash Image. Supports text-to-image, image editing, multi-image fusion with up to 14 reference images, Google Search grounding, and outputs up to 4K resolution.
Starting from
0 credits
seedream
seedream
Starting from
0 credits
grok
grok
Grok Imagine is xAI’s AI video generation model for creating high-quality videos with realistic motion, native audio, and synchronized speech. Grok Imagine 1.5 introduces faster generation speeds, improved motion physics, and stronger visual consistency for modern AI video applications.
Starting from
0 credits
qwen
qwen
Generate realistic 2K images with structured text
Starting from
0 credits
OpenAI
OpenAI
Bring your ideas to life with sharper, faster, more precise image generation using the GPT Image 2.5 API.
Starting from
0 credits
wan
wan
Generate images with cinematic precision through high-fidelity text-to-image synthesis and structural editing.
Starting from
0 credits
seedream
seedream
Gemini said Generate images with lightning-fast efficiency and high-fidelity detail through a streamlined, lightweight architecture optimized for instant creative expression.
Starting from
0 creditsqwen
qwen
Generate realistic 2K images with structured text
Starting from
0 credits
Luma
Luma
Starting from
0 credits
seedream
seedream
Starting from
0 credits