One API key. SDK
Your choice of model.
The request and response format of the Hoveydai API follows the common chat-completions convention. You set the Base URL and the key, pick the model with an id on every request, and see the cost of each key separately.
- Base URL and keySet these two values and a model id, then check the docs for the supported endpoints and parameters.
- ModelOne string per request; the rest of your client code stays the same.
- CostEach key's usage is tracked separately and paid from your shared account credit.
import requests -BASE = "https://api.example.com/v1"-API_KEY = "sk-..."+BASE = "https://hoveydai.ir/v1"+API_KEY = "hvd_..." reply = requests.post( f"{BASE}/chat/completions", headers={"Authorization": f"Bearer {API_KEY}"}, json={"model": "nvidia-nemotron-3-nano-omni-30b-a3b-reasoning-free", "messages": [...]}, # any model id from the list)
From key to first reply in three steps.
Create a key
In the dashboard, create a separate key for each app so its cost is shown separately.
Change the base URL
Set the base URL and the key in your client (SDK) settings. Use a model ID from the catalog and review supported parameters. An SDK is a client library that makes connecting your app to the API easier.
Send a request
Write the model ID and send. The reply comes back in the common chat-completions format and the cost is recorded against that key.
Any HTTP client, in any language.
Works with a plain HTTP request, for example requests in Python or fetch in JavaScript, streaming or not. Support covers the chat/completions and models endpoints and the documented parameters; other features, such as embeddings or tools, are not supported.
import requests BASE = "https://hoveydai.ir/v1"changedAPI_KEY = "hvd_..." reply = requests.post( f"{BASE}/chat/completions", headers={"Authorization": f"Bearer {API_KEY}"}, json={"model": "nvidia-nemotron-3-nano-omni-30b-a3b-reasoning-free", "messages": [{"role": "user", "content": "hello"}]},)print(reply.json()["choices"][0]["message"]["content"])
Different models. One connection.
Change the model in your request. Manage your API keys, usage reports and account credit in the same platform.
- One key for allChange the model name in the request, not the library.
- Shared account creditChat and API usage draw from the same account.
- One price tableInput and output price of every model, visible before you use it.
base_url="https://hoveydai.ir/v1"Choose a model. Understand the cost.
Pick a model to update the estimator below.
Estimate monthly cost with the selected model
Assumption: about 800 input and 600 output tokens per message, a 30-day month. Prices come from the live catalog.
If you reach a limit, the error tells you why.
Errors are returned as standard JSON with the fields message, type, param, code and request_id, and each one says what happened and what to do. The final list of codes is in the docs.
| Code | Means | What to do |
|---|---|---|
| 400 | Invalid request | Check the body and parameters against the docs. |
| 401 | Invalid or missing key | Check the Authorization header and the key. |
| 402 | Not enough credit | Review account credit and plan limits; see the HTTP 402 errors in the docs. |
| 404 | Model not found | Take the model id from the model list. |
| 429 | Too many requests | Wait a moment and send again; check your plan's limit. |
| 5xx | Error on our side or the provider's | Try again in a few seconds. |
- Active planDaily and monthly requests See dashboard and docs
- Each requestMaximum context window See dashboard and docs
- APIRate and concurrency See dashboard and docs
{ "error": { "message": "Invalid API key", "type": "invalid_request_error" }}
One key per app. Clear usage per key.
See how much each key used and what it cost, for example your support bot compared with a test script.
- Usage and costTokens and USD for each key, separately.
- Deleting archives a keyAn archived key stops working, but its usage history stays.
| Name | Key | Tokens this month | Cost (USD) | Status |
|---|---|---|---|---|
| Support botCreated Aug 20, 2026 | hvd_…a41f | 48,200,000 | 23.1 | Active |
| Mobile appCreated Sep 2, 2026 | hvd_…9c02 | 12,600,000 | 7.4 | Active |
| Test scriptCreated Sep 26, 2026 | hvd_…5b77 | 310,000 | 0.15 | Archived |