ScalingTensor API documentation

01

Generate your first media job

Create an API key in the Console, then submit a job for a media model from the catalog. The example uses sonilo/text-to-music. Save data.jobId from the response and poll the result endpoint every few seconds until status is completed or failed; the completed result contains the output URL.

# 1. Submit a job. The response contains data.jobId.
curl -X POST https://restapi.scalingtensor.com/api/media/generate \
  -H "Content-Type: application/json" \
  -H "apiKey: YOUR_API_KEY" \
  -d '{
    "model": "sonilo/text-to-music",
    "params": {
      "prompt": "lofi hiphop beat with warm vinyl texture",
      "duration": 20,
      "variants_num": 1
    }
  }'

# 2. Poll with that jobId until data.status is completed or failed.
curl "https://restapi.scalingtensor.com/api/media/result?jobId=YOUR_JOB_ID" \
  -H "apiKey: YOUR_API_KEY"

02

Fundamentals

Base URL

Use the production API root below. Requests and responses use JSON. Media generation currently accepts JSON URLs only; binary uploads are not supported.

https://restapi.scalingtensor.com

Authentication

Except for the model list, chat and media calls require the key created in the Console in the apiKey request header. Do not use Authorization or expose keys in browser code.

Content-Type: application/json
apiKey: YOUR_API_KEY

Response envelope

Every endpoint returns the same envelope. A request is successful only when code is 0; an HTTP success alone does not indicate business success. time and Long identifiers may be serialized as strings.

{
  "code": 0,
  "data": { ... },
  "msg": "Success",
  "time": "1788483942311",
  "requestId": "",
  "success": true
}

03

API Reference

Create a chat completion

This endpoint is synchronous and works with catalog models whose type is chat; replace YOUR_CHAT_MODEL_ID with one of their slugs. messages are passed to the active model adapter. The current controller accepts only model and messages as top-level fields.

curl -X POST https://restapi.scalingtensor.com/api/chat/completion \
  -H "Content-Type: application/json" \
  -H "apiKey: YOUR_API_KEY" \
  -d '{
    "model": "YOUR_CHAT_MODEL_ID",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Response data

{
  "code": 0,
  "data": {
    "content": "Hello! How can I help?",
    "tokensIn": 8,
    "tokensOut": 7,
    "costMicros": "6"
  },
  "msg": "Success"
}

Submit a media job

Media generation is asynchronous. Save the returned jobId and poll the result endpoint. params are forwarded according to the model provider, so available fields depend on the selected model.

curl -X POST https://restapi.scalingtensor.com/api/media/generate \
  -H "Content-Type: application/json" \
  -H "apiKey: YOUR_API_KEY" \
  -d '{
    "model": "sonilo/text-to-music",
    "params": {
      "prompt": "Warm ambient music for a product demo",
      "duration": 30,
      "variants_num": 1
    }
  }'

Response data

{
  "code": 0,
  "data": { "jobId": "724958320123", "status": "pending" },
  "msg": "Success"
}

Retrieve a media result

Poll with the jobId returned during submission. A job can only be read by the user that owns the API key used to create it. Poll every 2–5 seconds until completed or failed.

curl "https://restapi.scalingtensor.com/api/media/result?jobId=724958320123" \
  -H "apiKey: YOUR_API_KEY"

Job statuses

{
  "code": 0,
  "data": {
    "status": "completed",
    "resultData": {
      "status": "completed",
      "output_url": "https://.../result.mp3"
    }
  },
  "msg": "Success"
}

04

Common media parameters

params differ by model. Each model page lists its accepted parameters (Input Schema) and an example request. The Sonilo parameters below are validated before a job is accepted.

05

Error handling

Business errors use the same response envelope. Check code before reading data. Common codes are listed below.

Security and retry guidance

• Keep API keys on your server or in a secure secret manager.
• Decide carefully whether to retry chat calls to avoid duplicate charges.
• After a media submission succeeds, do not resubmit; store jobId and poll it.
• Use exponential backoff only for rate limits, network failures, and server errors.