# Seedream 5.5

> Run Seedream 5.5 by bytedance online or via API. $0.020 per 1K/1.5K image, $0.035 per 2K image, plus $0.008 per reference image, no setup.

**URL:** https://inference.sh/apps/bytedance/seedream-5-5
**Last updated:** 2026-11-12

---

ByteDance Seedream 5.5 image model via BytePlus ModelArk. Text-to-image, editing and multi-reference generation with up to 10 images, transparent PNG output, 1K to 2K resolution.

- app: `bytedance/seedream-5-5`
- maker: [bytedance](https://inference.sh/apps/bytedance.md)
- category: [image](https://inference.sh/apps/category/image.md)
- input → output: text → image, image → image
- tasks: [text to image](https://inference.sh/apps/tag/text-to-image.md), [image to image](https://inference.sh/apps/tag/image-to-image.md), [image editing](https://inference.sh/apps/tag/image-editing.md)
- price: $0.020 per 1K/1.5K image, $0.035 per 2K image, plus $0.008 per reference image
- runs via: api, javascript and python sdk, belt cli, mcp

## seedream-5-5 API Guide

### About
bytedance seedream 5.5 image model via byteplus modelark. text-to-image, editing and multi-reference generation with up to 10 images, transparent png output, 1k to 2k resolution.

### Get an API Key
Create one in [settings → api keys](https://app.inference.sh/settings/keys). The examples read it from `INFERENCE_API_KEY`.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Run and Get Result
Submit a request and wait for the final result.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @38ttz340 pinned
result = client.run({
        "app": "bytedance/seedream-5-5@38ttz340",
        "input": {
            "prompt": "A glass perfume bottle on a pale stone pedestal, soft morning light, product photography"
        }
    })

print(result["output"])
```

#### Stream Live Updates
Get real-time progress updates as the task runs.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @38ttz340 pinned
## stream=True yields updates as they arrive
for update in client.run({
        "app": "bytedance/seedream-5-5@38ttz340",
        "input": {
            "prompt": "A glass perfume bottle on a pale stone pedestal, soft morning light, product photography"
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

#### Run in the Background
Start the task and get its id back right away, then check on it with `GET /tasks/{id}`. It is done when `status` is 10 (completed), 11 (failed) or 12 (cancelled).

```python
import os
from inferencesh import inference, TaskStatus

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## returns as soon as the task is created
task = client.run({
        "app": "bytedance/seedream-5-5@38ttz340",
        "input": {
            "prompt": "A glass perfume bottle on a pale stone pedestal, soft morning light, product photography"
        }
    }, wait=False)

## later: read its current state
state = client.tasks.get(task["id"]).data
if state["status"] == TaskStatus.COMPLETED:
    print(state["output"])
```

### 2. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "bytedance/seedream-5-5@38ttz340",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

```python
## upload and get a hosted URL
file = client.files.upload("/path/to/file.png")
print(file.uri)  # https://cloud.inference.sh/...
```

### 3. Schema

#### Input
- **prompt** (string) *required*: Text prompt describing the image to generate or the edit to perform. Best under about 600 English words. Supports text rendering in 16 languages.
- **images** (array): Optional reference images for editing or multi-reference generation, up to 10. jpeg, png, webp, bmp, tiff or gif; aspect ratio between 1:16 and 16:1.
- **size** (string): Output resolution tier. 1K and 1.5K are billed at the lower rate, 2K at the higher rate.
- **aspect_ratio** (string): Output aspect ratio.
- **output_format** (string): Output image format. Transparent backgrounds need png.
- **background** (string): Transparency of the output. auto lets the model decide from the prompt, transparent returns an RGBA png, opaque returns an RGB image.
- **watermark** (boolean): Add an 'AI generated' watermark to the lower-right corner.

#### Output
- **image** (string): The generated image file.

## other image apps

- [MiniMax H3 Image](https://inference.sh/apps/minimax/h3-image.md): $2.30/M text in, $1.50/M image in, $3.80/M image out (token-based)
- [GPT Image 2.6 Flare](https://inference.sh/apps/openai/gpt-image-2-6-flare.md): $30.00/M output, $5.00/M text input, $8.00/M image input, $0.10/M SVG input, $0.50/M SVG output
- [GPT Image 2.6 Sunburst](https://inference.sh/apps/openai/gpt-image-2-6-sunburst.md): $30.00/M out, $5.00/M text in, $8.00/M img in; SVG $0.10/$0.50/M in/out
- [Gemini Nano Banana 2.1](https://inference.sh/apps/google/gemini-nano-banana-2-1.md): $1.50/M input, $0.0336–$0.1134/image (1K–4K), +$0.014/query Google Search
- [Grok Imagine Image 2.0](https://inference.sh/apps/xai/grok-imagine-image-2-0.md): $0.04/img low 1k, $0.06/img low 2k, $0.06/img med 1k, $0.08/img med 2k; $0.01/source img (edits)

## faq

### how much does Seedream 5.5 cost?

$0.020 per 1K/1.5K image, $0.035 per 2K image, plus $0.008 per reference image. you pay per run from your inference shell credits. no subscription is required.

### how do I run Seedream 5.5 via api?

call bytedance/seedream-5-5 with the javascript or python sdk, the rest api, or `belt app run bytedance/seedream-5-5` from a terminal. the api reference on this page lists every input.

### who makes Seedream 5.5?

Seedream 5.5 is made by bytedance and runs on inference shell. every bytedance app is listed at https://inference.sh/apps/bytedance.

### can my agent use Seedream 5.5?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

### what are the alternatives to Seedream 5.5?

other image apps on inference shell include MiniMax H3 Image, GPT Image 2.6 Flare, GPT Image 2.6 Sunburst, Gemini Nano Banana 2.1. they run through the same api, so switching is a one-line change.