Name: ByteDance Seed-X-PPO-7B Text Translation API
Brand: magicapi
SKU: api-magicapi-multilingual-translation-api-lucataco-seed-x-ppo
Availability: InStock
Author: API Market

Shashank Agarwal

# 🌍 Text Translation API (ByteDance Seed-X-PPO-7B)

## Overview
Seed-X-PPO-7B is an open-source multilingual translation language model from ByteDance Seed. Its developer describes the Seed-X series as powerful multilingual translation models.

Send the `text` and a `target_language`. Set `source_language` or leave it at `auto` for automatic detection. The API returns the translation as one plain text string.

## Features
- **28 languages**: English, Chinese, German, French, Spanish, Arabic, Portuguese, Italian, Russian, Japanese, Korean, Hindi, Thai, Vietnamese, Turkish, Polish, Dutch, Swedish, Danish, Norwegian, Finnish, Czech, Slovak, Hungarian, Romanian, Bulgarian, Croatian and Slovenian.
- **Automatic source detection**: `source_language` defaults to `auto`.
- **Beam search**: `num_beams` from 1 to 8 (default 4).
- **Length cap**: `max_length` from 50 to 512 (default 512) limits the generated text.
- **Plain text output**: `output` is the translated string.

## Use Cases
1. **Customer messages**: translate support tickets, emails and chat messages.
2. **Product content**: localize descriptions, notices and UI text.
3. **Internal communication**: share announcements across teams in different languages.
4. **Content review**: read foreign-language text in your own language.

## Visual Examples
### Example Input
An English office notice translated to Spanish, with `source_language` `auto`, `num_beams` 4 and `max_length` 512.

```json
{
  "text": "Our office will be closed on Monday for maintenance. Please send any urgent requests before Friday afternoon, and we will reply as soon as we are back.",
  "num_beams": 4,
  "max_length": 512,
  "source_language": "auto",
  "target_language": "Spanish"
}
```

### Example Output
```text
Nuestra oficina estará cerrada el lunes por mantenimiento. Por favor, envíe cualquier solicitud urgente antes del viernes por la tarde, y responderemos tan pronto como volvamos.
```

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `text` | string | Yes |  |  | Text to translate |
| `target_language` | string | Yes |  | `auto`, `English`, `Chinese`, `German`, `French`, `Spanish`, `Arabic`, `Portuguese`, `Italian`, `Russian`, `Japanese`, `Korean`, `Hindi`, `Thai`, `Vietnamese`, `Turkish`, `Polish`, `Dutch`, `Swedish`, `Danish`, `Norwegian`, `Finnish`, `Czech`, `Slovak`, `Hungarian`, `Romanian`, `Bulgarian`, `Croatian`, `Slovenian` | Target language (e.g., 'Chinese', 'French', 'Spanish') |
| `source_language` | string | No | `auto` | `auto`, `English`, `Chinese`, `German`, `French`, `Spanish`, `Arabic`, `Portuguese`, `Italian`, `Russian`, `Japanese`, `Korean`, `Hindi`, `Thai`, `Vietnamese`, `Turkish`, `Polish`, `Dutch`, `Swedish`, `Danish`, `Norwegian`, `Finnish`, `Czech`, `Slovak`, `Hungarian`, `Romanian`, `Bulgarian`, `Croatian`, `Slovenian` | Source language (use 'auto' for automatic detection) |
| `max_length` | integer | No | `512` | 50 to 512 | Maximum length of generated text |
| `num_beams` | integer | No | `4` | 1 to 8 | Number of beams for beam search |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.0044 per API unit.
- **1 API unit = 1 request with up to 4 seconds of processing.** A request that takes longer is billed one more unit for each started 4-second block (for example, 10 seconds of processing is 3 units, $0.0132).
- **Example cost**: the example request took 1.9 seconds of processing, which is 1 unit ($0.0044).
- Longer texts take longer to translate and can use more units.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/multilingual-translation-api-lucataco-seed-x-ppo`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 1 second and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/multilingual-translation-api-lucataco-seed-x-ppo/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "bd6fdc731bd97a7dc3ea84285479567a3d40165d851bc7251122defd30372e8c",
    "input": {
      "text": "Our office will be closed on Monday for maintenance. Please send any urgent requests before Friday afternoon, and we will reply as soon as we are back.",
      "num_beams": 4,
      "max_length": 512,
      "source_language": "auto",
      "target_language": "Spanish"
    }
  }'
```

Response (201 Created):
```json
{
  "id": "1r5jvj64a9rmr0d1mvtr7ctsr4",
  "version": "bd6fdc731bd97a7dc3ea84285479567a3d40165d851bc7251122defd30372e8c",
  "status": "starting",
  "created_at": "2026-11-04T14:28:06.866Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/multilingual-translation-api-lucataco-seed-x-ppo/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "1r5jvj64a9rmr0d1mvtr7ctsr4",
  "status": "succeeded",
  "output": "Nuestra oficina estará cerrada el lunes por mantenimiento. Por favor, envíe cualquier solicitud urgente antes del viernes por la tarde, y responderemos tan pronto como volvamos.",
  "error": null,
  "created_at": "2026-11-04T14:28:06.866Z",
  "started_at": "2026-11-04T14:28:34.282Z",
  "completed_at": "2026-11-04T14:28:36.202Z"
}
```

`output` is a single string with the translated text.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `target_language`, a language that is not in the list, or a `num_beams` outside 1 to 8.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
Requests are rate limited to keep usage fair. If you receive a 429 response, wait and retry with exponential backoff.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/multilingual-translation-api-lucataco-seed-x-ppo";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "bd6fdc731bd97a7dc3ea84285479567a3d40165d851bc7251122defd30372e8c", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 1000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  "text": "Our office will be closed on Monday for maintenance. Please send any urgent requests before Friday afternoon, and we will reply as soon as we are back.",
  "num_beams": 4,
  "max_length": 512,
  "source_language": "auto",
  "target_language": "Spanish"
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/multilingual-translation-api-lucataco-seed-x-ppo"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "bd6fdc731bd97a7dc3ea84285479567a3d40165d851bc7251122defd30372e8c", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 1
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


print(create_and_wait_for_prediction({
    "text": "Our office will be closed on Monday for maintenance. Please send any urgent requests before Friday afternoon, and we will reply as soon as we are back.",
    "num_beams": 4,
    "max_length": 512,
    "source_language": "auto",
    "target_language": "Spanish"
}))
```

## FAQ
- **Which languages are supported?**
  - The 28 languages in the `target_language` and `source_language` lists. Use the English language name exactly as listed, for example `Spanish` or `Chinese`.
- **Do I need to set the source language?**
  - No. `source_language` defaults to `auto`, which detects it automatically.
- **How long can the translation be?**
  - `max_length` (50 to 512, default 512) is the maximum length of the generated text. Split long documents into smaller pieces.
- **How much does a request cost?**
  - $0.0044 for each started 4 seconds of processing. The example took 1.9 seconds and cost 1 unit ($0.0044).
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page.


Translate text between 28 languages with ByteDance Seed-X-PPO-7B, with automatic source language detection. $0.0044 per request, pay as you go.