Docs
SuperTomorrow API Docs
Use one OpenAI-compatible API to access enabled models. This documentation follows the integration flow: create a key, send requests, review billing, handle errors, and connect SDK or IDE tools.
Quick Start
First API call
1. Create an API key
Log in to the Dashboard and create a key. The full key is shown only when created or regenerated, and can be copied immediately.
2. Select models
When creating a key, select one or multiple models. The key can only call the models it is scoped to.
3. Send a request
Use the Base URL, Bearer key, and model alias to send an OpenAI-compatible request.
curl https://api.supertomorrow.cc/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-chat",
"messages": [{"role": "user", "content": "Hello"}],
"max_tokens": 160
}'Integrations
Client / IDE integrations
OpenAI SDK
Replace base_url directly in Python / Node projects.
curl
Minimal validation for API key, model scope, and response format.
Python
Use the OpenAI Python SDK.
Node.js
Use the OpenAI Node SDK.
Cursor
Use the OpenAI Compatible provider.
Cline
Configure custom Base URL, API key, and model alias.
Cherry Studio
Desktop client OpenAI-compatible setup.
Continue
VS Code extension model configuration.
LangChain
Use LangChain OpenAI adapters.
Billing
Balance & billing
| Credits | The platform uses Credits as the usage unit. The default reference is 1 USD = 100 Credits. |
|---|---|
| Charging | Successful requests are charged by actual input and output tokens. Failed requests are not charged. |
| Pricing source | Model prices come from the backend model catalog and can be adjusted by operations. |
| Insufficient balance | When balance is insufficient, the API returns 402 insufficient_credits before calling upstream models. |
API Reference
API Reference
Base URL
https://api.supertomorrow.cc/v1
POST /v1/chat/completions
Send chat completion requests using the OpenAI-compatible format.
GET /v1/models
Return models available to the current API key.
Endpoint
Chat Completions
| model | Required. Model alias, for example deepseek-chat. |
|---|---|
| messages | Required. OpenAI-compatible messages array. |
| max_tokens | Optional. Maximum output tokens. |
| stream | Optional. Set true to receive streamed responses. |
Endpoint
Models
This endpoint returns models currently available to the API key. Unscoped, unavailable, or unpublished models are not returned.
curl https://api.supertomorrow.cc/v1/models \
-H "Authorization: Bearer YOUR_API_KEY"Limits
Rate limits
The platform applies rate limits by API key, user account, and provider route. When a request is rate-limited, the API returns 429 and clients should retry with exponential backoff.
Errors
Error codes
| 401 | The API key is invalid, disabled, or malformed. |
|---|---|
| 402 | Insufficient balance. Recharge before sending more requests. |
| 403 | The key is not allowed to use the model, or the model is unavailable. |
| 429 | Rate limit exceeded. Retry with backoff. |
| 502 | The upstream provider is unavailable or all fallback routes failed. Failed requests are not charged. |
SDK
OpenAI SDK
Most existing OpenAI SDK projects only need api_key, base_url, and model alias changes.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.supertomorrow.cc/v1",
)
response = client.chat.completions.create(
model="deepseek-chat",
messages=[{"role": "user", "content": "Hello"}],
max_tokens=160,
)
print(response.choices[0].message.content)IDE
Cursor
In Cursor, choose an OpenAI-compatible or custom model provider, set Base URL to https://api.supertomorrow.cc/v1, and use a Dashboard API key.
IDE
Cline
In Cline, select OpenAI Compatible as the API provider, then set Base URL, API key, and an enabled model alias.