Chinese model APIs on one OpenAI-compatible key. Browse models

FAQ

Answers about SmarToken accounts, model APIs, billing and production use

This page collects the questions users usually ask before creating an API key or moving real traffic to an OpenAI-compatible Chinese model gateway.

Accounts and access

Use these answers when a user is trying to sign in, create a key or understand account permissions.

Which sign-in methods are supported?

SmarToken uses Google sign-in for normal user accounts. Existing users sign in with Google, and new accounts are created automatically on the first eligible Google sign-in.

Why is there no public password login?

Google sign-in reduces password handling for the public console. API traffic still uses server-side API keys, so user sessions and model calls remain separate.

How do I get an API key?

Sign in, open the console and create a key in the API key area. The full key is shown once. Store it in a server-side secret manager or environment variable, not in browser code.

Can I revoke a key after it is exposed?

Yes. Revoke the exposed key, rotate the secret in every service that used it and review recent usage logs for unexpected traffic.

API and model routing

These answers cover the OpenAI-compatible endpoint, model IDs and response behavior.

What base URL should I use with the OpenAI SDK?

Set the SDK baseURL to https://thesmartoken.com/v1 and authenticate with Authorization: Bearer YOUR_SMARTOKEN_KEY. Chat requests use the standard /chat/completions path under that base URL.

Which model ID should I send?

Use an exact ID returned by GET /v1/models, such as deepseek-chat when enabled. Catalog entries marked for research or integration are not necessarily callable.

Does SmarToken support streaming?

Yes. Send stream: true for server-sent event streaming or stream: false for a normal JSON response. Streaming is useful for chat UIs and developer tools that show partial output.

Can I call multiple Chinese model families with one integration?

Use the same OpenAI-compatible client, Base URL and API key for enabled text routes, and select an ID returned by GET /v1/models. Other catalog entries may be research only or still integrating.

How can I see which model IDs are available?

GET /v1/models returns the currently enabled model IDs. Browse /models for human-readable details and route status.

Billing and credits

These answers explain wallet balance, promotional credit and pricing checks.

How is API usage charged?

Usage is estimated from input and output tokens, priced by model route and deducted from wallet balance after the request or stream completes.

What happens when balance is too low?

Requests can be rejected when the account lacks enough usable balance. Add balance, reduce output length or choose a lower-cost model route before retrying.

Can promotional credit be withdrawn?

Promotional API credit is usage balance for model calls and is not withdrawable cash unless a specific campaign policy says otherwise.

Where can I compare model prices?

Use the pricing page for current public model prices and each model detail page for input and output token rates, context notes and source links.

Which payment methods are supported?

Currently, new top-ups use Stripe Checkout through Stellar Ever Co., Limited. Available payment options may vary by location. Contact support if you need help.

Troubleshooting

Use these answers when API calls fail, stream output stops or costs look unexpected.

What should I do after a 401 error?

Check that the Authorization header uses Bearer plus the full SmarToken API key, confirm the key has not been revoked and make sure the request is sent from server-side code.

What should I do after a 429 error?

A 429 usually means rate limiting or temporary load protection. Reduce concurrency, add backoff and include timestamps, model ID and request path if you open a support ticket.

Why did a request cost more than expected?

Long prompts, long generated answers, retries and streaming responses can increase token usage. Compare input size, max output settings and actual usage logs for the request.

Why is an upstream model temporarily unavailable?

Routes depend on upstream provider availability and configured keys. Retry with backoff, switch to a comparable model or contact support if the issue affects production traffic.

What information should I include in a support ticket?

Include account email, request time, model ID, endpoint path, error code, approximate prompt size and whether the issue happened with streaming or non-streaming mode. Do not include private API keys.

Production readiness

These answers help teams move from a quick demo to safer production use.

Should API keys be stored in frontend code?

No. Keep keys on your server, worker or secure automation environment. Frontend apps should call your backend, and your backend should call SmarToken.

How should I choose a default production model?

Run the same evaluation set across candidate models and compare quality, latency, cost and failure modes. Pick a route for a workload, not for the whole company by default.

How often should model routes be reviewed?

Review important routes after major provider releases, pricing updates or quality regressions. Keep a small benchmark set from real support, coding or document tasks.