Seedance 2.5 is live — 30-second cinematic video with native audio & real-person references

Seedream 5.0 Pro — Text & Image to Image Generation

Seedream 5.0 Pro is ByteDance's flagship image model — turn a prompt or up to ten reference images into sharp 1K–2K visuals with reliable text rendering. Submit a prompt and poll one task for the finished image.

Highlights
ByteDance flagship · basic / high quality tiers
Best for
Photoreal portraits, e-commerce, art
Input
Text, plus up to 10 reference images
Output
One image per request
Input

≤ 4000 chars

1:1 · 4:3 · 3:4 · 16:9 · 9:16 · 2:3 · 3:2

0/10 files

Up to 10 · public URLs

basic · high

Always on in Playground. Do not generate restricted content: flagged images are hidden, but generation is still charged. API users can disable it with content_filter=false.

Estimated cost~$0.03232 credits
Result

Try one of these prompts

What is the Seedream 5.0 Pro API?

Seedream 5.0 Pro is ByteDance's flagship image model, exposed on reAPI as one async endpoint for text-to-image and multi-reference image-to-image with up to 10 reference images. Each request picks one of seven aspect ratios and a quality tier — basic for 1K or high for 2K — and returns a single image, billed per image.

What you can build with this model

Real-world workflows and production use cases you can build and ship with this model.

Photorealistic image generated by Seedream 5.0 Pro

Photoreal shots from a single prompt

Seedream 5.0 Pro renders convincing photography — dramatic perspectives, natural light, and lifelike skin — straight from text. Describe the scene and get a finished frame in one call.

Try a prompt
Magazine cover with rendered text from Seedream 5.0 Pro

Typography and graphic design that reads

Seedream 5.0 Pro renders legible headlines, logos, and layout text, so posters, magazine covers, and ads come back print-ready. Dependable text rendering is where it pulls ahead of older image models.

Portrait generated by Seedream 5.0 Pro

Portraits and characters with reference control

Pass up to ten reference images and the model fuses them into a consistent character or restyled portrait. Multi-reference image-to-image keeps faces and wardrobe on-model across a series.

Pricing

Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.

First test cost
$0.03232 credits

One sample at the cheapest tier (1 image).

Testing budget guide
Add credits
$10
≈ 319 tests
$50
≈ 1596 tests
$100
≈ 3192 tests
ModelCategoryPrice
Seedream 5.0 Pro1K image (≤ 2.36M px)
$0.032
32 credits · 1 image
2K image (> 2.36M px)
$0.063
63 credits · 1 image
1K image (≤ 2.36M px) · Output check disabled · API only
$0.034
34 credits · 1 image
2K image (> 2.36M px) · Output check disabled · API only
$0.067
67 credits · 1 image

Why reAPI

Flagship image quality

Seedream 5.0 Pro is ByteDance's top Seedream tier — sharper detail, stronger prompt adherence, and dependable text rendering at up to 2K. It is the model to reach for when the output has to look finished.

Transparent per-image pricing

1 credit equals $0.001. Pricing follows the official output tier, with the first reference included and an official surcharge for each additional reference. Images blocked by the output check are still charged because generation completed.

Async images API

Submit a prompt to the images endpoint and reAPI returns a task_id. Poll the task until it reaches a terminal state. Completed tasks return the image in output.image_urls. Generation or system failures are refunded automatically; images blocked by the output check are hidden and still charged.

Seedream 5.0 Pro vs Nano Banana Pro

How ByteDance's Seedream 5.0 Pro compares with Google's Nano Banana Pro for prompt-driven image generation.

Capability
Seedream 5.0 Pro
Nano Banana Pro
Text rendering
Reliable legible headlines, logos, and layout text
Strong text rendering
Reference images
Up to 10 for multi-reference fusion
Multi-image reference supported
Max resolution
High-quality 2K tier
Up to 4K
Delivery
Async task_id — poll for the image URL
Synchronous
Pricing model
Official output-tier price plus additional-reference surcharge
Per-image, premium tier
Access
OpenAI-style images endpoint on reAPI
Available through Google tooling

Comparison reflects publicly documented behavior at the time of writing and may change.

Call Seedream 5.0 Pro in three steps

  1. step 01

    Create an API key

    Sign up and grab a key. Free credits cover your first Seedream 5.0 Pro images — no card required.

    Open
  2. step 02

    POST your prompt

    Send a prompt to /api/v1/images/generations with the model set to doubao-seedream-5-0-pro. Choose an aspect_ratio and set quality to basic or high; add reference images when you need them.

    Open
  3. step 03

    Use the image URL

    reAPI returns a task_id. Poll GET /api/v1/tasks/:id until it is completed, then download the image from output.image_urls.

    Open
docs/api/seedream-5-0-pro

API reference

Drop-in code and the full parameter table.

curl -X POST https://reapi.ai/api/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-5-0-pro",
    "prompt": "a scarlet macaw on a mossy branch, cinematic god rays",
    "aspect_ratio": "16:9",
    "quality": "high"
  }'

Parameter validation failed

Rejected synchronously with the failing field named. Check enum values, ranges, and URL fields — nothing is charged.

Authentication or balance issue

401 means a missing or invalid Bearer key; 402 means the reserve exceeds your balance. Manage keys and credits in the console.

Content or material rejected

Reference material and outputs pass automated moderation. Rejected tasks fail with a clear error and a full refund.

Task failed or timed out

A task that reaches a failed state is never charged — the reserve refunds automatically. Keep the task id and retry when ready.

Frequently asked questions

Common questions about this model.

Seedream 5.0 Pro is ByteDance's flagship Seedream image model. It turns text and up to ten reference images into 1K–2K images with strong text rendering. On reAPI, it is served through an async images endpoint.

start building

Ready to ship?

Try it in the playground or grab an API key to integrate now.