Seedream 3.0
Seedream 3.0 is ByteDance's high-resolution bilingual image generation model, built for Chinese and English prompt understanding with stronger text rendering, better structural accuracy, improved visual aesthetics, and native high-definition image creation.
Seedream 3.0 Text to Image API
Describe the image (max 300 Chinese characters or 600 English words)
Output image size preset, or use width/height for custom. Range: 648x648 to 2048x2048, 64-aligned
How closely to follow the prompt (1-10)
Result
Results will appear here
Cost: $0.03/image
Seedream 3.0 API Implementation Guide
Get API Key
Generate your API key from the dashboard and set it as an environment variable.
export MODELHUNTER_KEY="your_api_key"Make Your First Call
Follow the API documentation for complete code examples in cURL, JavaScript, and Python, including request format, polling, and error handling.
View API Documentation →Seedream 3.0 Key Info
Capabilities
- Text to Image API
Pricing
Text to Image API
$0.03 / image
$0.03 per image
Use Cases
Output Formats
Seedream 3.0 API Documentation
Run the playground first, then open the full API docs for integration details.
About
Cost-effective text-to-image with seed and guidance control
Code Examples
1curl -X POST https://api.modelhunter.ai/api/v1/seedream/text-to-image \2-H "Authorization: Bearer YOUR_API_KEY" \3-H "Content-Type: application/json" \4-d '{5"model": "seedream-3-0-t2i",6"input": {7"prompt": "A futuristic cityscape at sunset with neon signs",8"size": "1024x1024"9}10}'
Schema
View Full API DocsInput
modelModel ID for this capability.
Value: seedream-3-0-t2i
promptDescribe the image (max 300 Chinese characters or 600 English words)
sizeOutput image size preset, or use width/height for custom. Range: 648x648 to 2048x2048, 64-aligned
Options: 1024x1024, 1152x864, 864x1152, 1280x720, 720x1280, 1248x832, 832x1248, 1512x648
Default: 1024x1024
widthCustom width in pixels (alternative to size). Range: 648-2048, 64-aligned
Range: 648 to 2048
heightCustom height in pixels (alternative to size). Range: 648-2048, 64-aligned
Range: 648 to 2048
guidance_scaleHow closely to follow the prompt (1-10)
Default: 7
Range: 1 to 10
seedRandom seed for reproducibility. -1 for random
Default: -1
Range: -1 to 2147483647
watermarkWatermark
Default: true
response_formatResponse Format
Options: url
Default: url
webhookUrlURL to receive a webhook notification when the task completes.
metadataCustom key-value metadata to attach to the task for tracking.
Response (HTTP 202)
successWhether the request was accepted successfully.
data.idUnique task ID. Use this to poll GET /api/v1/tasks/{id} for results.
data.statusTask status: pending, processing, completed, failed.
data.typeGeneration type: text-to-image.
data.providerProvider name: seedream.
data.modelModel ID used for generation.
data.created_atISO 8601 timestamp of when the task was created.
data.estimated_secondsEstimated time in seconds until the task completes.