Name: BytePlus Seedream 3.0 – Text to Image | $0.03/call | API.market
Brand: byteplus
SKU: api-byteplus-seedream-text-to-image
Availability: InStock
Rating: 5.00 (1 reviews)
Author: API Market

Shashank Agarwal

# ✨💭 Seedream Text‑to‑Image API

## Overview

The **Seedream Text‑to‑Image API** turns any written prompt into a high‑resolution picture in seconds. Powered by the Seedream 3.0 diffusion model, it supports multiple aspect‑ratios, strict prompt‑to‑image guidance, and optional watermarking—making it a drop‑in service for apps that need production‑ready, AI‑generated visuals.

![Example output –Girl wearing t-shirt with Seedream-3.0 on API.market](https://blog.api.market/wp-content/uploads/2025/06/seedream-api-market.jpg)

*Generated with prompt: “A cinematic, photorealistic medium shot capturing the nostalgic warmth of a mid-2000s indie film. The focus is a young woman with a sleek, straight bob haircut in cool platinum white with freckled skin, looking directly and intently into the camera lens with a knowing smirk, her head is looking up slightly. She wears an oversized band t-shirt that says "Seedream 3.0 on API.market" in huge stylized text over a long-sleeved striped top and simple silver stud earrings. The lighting is soft, golden hour sunlight creating lens flare and illuminating dust motes in the air. The background shows a blurred outdoor urban setting with graffiti-covered walls (the graffiti says "seedream" in stylized graffiti lettering), rendered with a shallow depth of field. Natural film grain, a warm, slightly muted color palette, and sharp focus on her expressive eyes enhance the intimate, authentic feel.”*

---

## Features

* **Prompt‑to‑Image Generation** – create photorealistic or stylised art from natural‑language prompts.
* **Multiple Resolutions** – choose from 512×512 px up to 2048×2048 px, plus popular 16∶9, 4∶3, 3∶4, and cinematic 21∶9 formats.
* **Deterministic Seeds** – reproduce identical results by supplying a fixed seed.
* **Prompt Guidance Control** – balance creativity vs. prompt fidelity with `guidance_scale`.
* **Built‑in Watermarking** – optional “AI generated” badge for brand safety and compliance.
* **Signed URLs & Base64** – get a 24‑hour signed JPEG link or raw base‑64 data, ready for inline use.

---

## Use Cases

| Industry                          | SEO‑Optimised Scenario                                                                               |
| --------------------------------- | ---------------------------------------------------------------------------------------------------- |
| **E‑commerce**                    | Auto‑generate lifestyle product images and variant shots without costly photo shoots.                |
| **Mobile Gaming**                 | Rapidly create concept art, character portraits, or level thumbnails to accelerate design sprints.   |
| **Advertising & Marketing**       | Produce eye‑catching social posts and banner creatives on‑demand, perfectly sized for every channel. |
| **Publishing & Blogs**            | Illustrate articles with unique hero images that improve CTR and time‑on‑page.                       |
| **Interior Design / Real‑Estate** | Visualise décor ideas or staged rooms from simple text descriptions for client proposals.            |

---

## Pricing

| Tier    | Price / Image | Notes                                |
| ------- |------------- | ------------------------------------ |
| PAYG | **\$0.03**    | Pay‑as‑you‑go, no commitment.        |

*1 API unit = 1 image generated.*

---

## API Documentation

### Base URL

```
https://prod.api.market/api/v1/byteplus/seedream-text-to-image
```

### Authentication

Add your key to every request header:

```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Endpoints

| Method | Path                | Description                                                |
| ------ | ------------------- | ---------------------------------------------------------- |
| `POST` | `/predictions`      | Submit a new generation request.                           |
| `GET`  | `/predictions/{id}` | Poll prediction status & retrieve the image once complete. |

#### 1 . Create a prediction (POST / predictions)

```bash
curl -X POST \
  "https://prod.api.market/api/v1/byteplus/seedream-text-to-image/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "model": "seedream-3-0-t2i-250415",
    "prompt": "A serene koi pond at dusk, ultra‑realistic, 8K",
    "size": "1024x1024",
    "guidance_scale": 3,
    "watermark": true
  }'
```

**Response (202)**

```json
{
  "id": "pred_abc123",
  "status": "starting",
  "created": 1751020801
}
```

#### 2 . Check status (GET / predictions/{id})

```bash
curl -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  "https://prod.api.market/api/v1/byteplus/seedream-text-to-image/predictions/pred_abc123"
```

**Response (200 – succeeded)**

```json
{
  "id": "pred_abc123",
  "status": "succeeded",
  "output": {
    "model": "seedream-3-0-t2i-250415",
    "created": 1751020810,
    "data": [
      {
        "url": "https://signed.cdn.example/koi_pond.jpg"
      }
    ],
    "usage": { "generated_images": 1 }
  }
}
```

### Request Body Schema

| Field             | Type    | Required | Default     | Description                                                                                                 |
| ----------------- | ------- | -------- | ----------- | ----------------------------------------------------------------------------------------------------------- |
| `model`           | string  | ✓        | –           | Use `seedream-3-0-t2i-250415`.                                                                              |
| `prompt`          | string  | ✓        | –           | Text description (≤ 400 chars).                                                                             |
| `response_format` | string  |          | `url`       | `url` or `b64_json`.                                                                                        |
| `size`            | string  |          | `1024x1024` | Any res between **512×512** and **2048×2048**.<br>Popular presets: `864x1152`, `1280x720`, `1512x648`, etc. |
| `seed`            | integer |          | `-1`        | ‑1 (random) to 2 147 483 647.                                                                               |
| `guidance_scale`  | float   |          | `2.5`       | 1 – 10: higher → closer to prompt.                                                                          |
| `watermark`       | boolean |          | `true`      | Adds “AI generated” badge if **true**.                                                                      |

### Status Codes

| Code | Meaning               | When it happens                           |
| ---- | --------------------- | ----------------------------------------- |
| 200  | OK                    | Successful GET or synchronous POST.       |
| 202  | Accepted              | Generation queued; polling required.      |
| 400  | Bad Request           | Missing / invalid parameters.             |
| 401  | Unauthorized          | API key absent or invalid.                |
| 403  | Forbidden             | Key valid but lacks access to this model. |
| 404  | Not Found             | Invalid prediction ID.                    |
| 429  | Too Many Requests     | Rate limit exceeded.                      |
| 500  | Internal Server Error | Unexpected server issue.                  |
| 503  | Service Unavailable   | Temporary outage—retry later.             |

### Rate Limits

* Default: **60 requests per minute** per key.
* Exceeding the limit returns **429**. Retry with exponential back‑off (e.g., 1 s, 2 s, 4 s).

### Error Handling

```json
{
  "error": {
    "code": "invalid_parameter",
    "message": "The parameter 'prompt' is required",
    "status": 400
  }
}
```

**Best Practices**

1. Parse the `error.code` string for programmatic handling.
2. Retry **500** & **503** with back‑off (max 3 attempts).
3. Never retry **4xx** errors without fixing the request.

---

## Implementation Guide

### JavaScript (ES Module)

```javascript
import fetch from "node-fetch";

const API_KEY = "YOUR_API_MARKET_KEY";
const BASE = "https://prod.api.market/api/v1/byteplus/seedream-text-to-image";

export async function generateImage(prompt) {
  // 1. Create prediction
  const createRes = await fetch(`${BASE}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": API_KEY
    },
    body: JSON.stringify({ prompt, model: "seedream-3-0-t2i-250415" })
  });
  if (!createRes.ok) throw new Error(await createRes.text());
  const { id } = await createRes.json();

  // 2. Poll status
  const timeout = Date.now() + 10 * 60 * 1000; // 10 min
  while (Date.now() < timeout) {
    await new Promise(r => setTimeout(r, 1000));
    const statusRes = await fetch(`${BASE}/predictions/${id}`, {
      headers: { "x-api-market-key": API_KEY }
    });
    const data = await statusRes.json();
    if (data.status === "succeeded") return data.output.data[0].url;
    if (data.status === "failed") throw new Error(data.error || "Generation failed");
  }
  throw new Error("Timed out after 10 minutes");
}
```

### Python (Requests)

```python
import requests, time

API_KEY = "YOUR_API_MARKET_KEY"
BASE = "https://prod.api.market/api/v1/byteplus/seedream-text-to-image"

def generate_image(prompt):
    # 1. Create prediction
    r = requests.post(f"{BASE}/predictions",
                      headers={"x-api-market-key": API_KEY},
                      json={"prompt": prompt,
                            "model": "seedream-3-0-t2i-250415"})
    r.raise_for_status()
    prediction_id = r.json()["id"]

    # 2. Poll status
    deadline = time.time() + 600
    while time.time() < deadline:
        time.sleep(1)
        s = requests.get(f"{BASE}/predictions/{prediction_id}",
                         headers={"x-api-market-key": API_KEY}).json()
        if s["status"] == "succeeded":
            return s["output"]["data"][0]["url"]
        if s["status"] == "failed":
            raise RuntimeError(s.get("error", "Generation failed"))
    raise TimeoutError("Generation timed out")
```

### cURL Quick‑Start

```bash
# 1. Create prediction
curl -X POST \
  "https://prod.api.market/api/v1/byteplus/seedream-text-to-image/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{"prompt":"Sunrise over Mount Fuji, watercolor","model":"seedream-3-0-t2i-250415"}'

# 2. Check status (replace {id})
curl -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  "https://prod.api.market/api/v1/byteplus/seedream-text-to-image/predictions/{id}"
```

---

## Performance Optimization

* Prefer **768 px** or **1024 px** outputs for best speed‑to‑quality trade‑off.
* Keep prompts < 300 chars to reduce tokenisation overhead.
* Re‑use deterministic seeds when batching similar assets to maximise cache hits.

---

## FAQ

**Q : How large can my prompt be?**
A : Up to 400 UTF‑8 characters.

**Q : How long do signed URLs stay valid?**
24 hours from `created` timestamp.

**Q : Can I download the image directly instead of polling?**
Yes—once status is `succeeded`, the response already contains a ready‑to‑download URL.

**Q : Does the API support NSFW filtering?**
Yes, harmful or explicit prompts will return a 400 with `error.code = "safety_violation"`.

**Q : Where is the service hosted?**
All inference servers run in ISO‑27001‑certified data centres in the Asia‑Pacific region.

---

## Contact Us

If you have any questions or need assistance, you can reach out to us through the embedded chat on the bottom right corner of the page or send an email to hello\[at]api.market.


Convert any text prompt into ultra-sharp, 4K visuals in seconds. Supports multiple aspect ratios. From $0.03/call. Try it free on API.market.

BytePlus Seedream 3.0 – Text to Image | $0.03/call | API.market

PAYG

BytePlus

Have been using seedance's MCP integration with Claude. Works like a charm and saves me a lot of time. This creates production ready videos which can be used in corporate presentations. Recommending this for Marketing teams!!

Convert any prompt—product brief, concept sketch or blog idea—into ultra‑sharp, watermark‑optional visuals in seconds with the Seedream 3.0 diffusion engine.	