Status and incidents

Status: Operational support entry.

Use this page when you need to decide whether an API failure is caused by your request, your account, NexoRouter gateway limits, or a model-specific upstream issue.

NexoRouter status page

Where to check first

Question	Check
Is the public site or gateway unavailable?	Status
Did the request reach NexoRouter?	Usage Logs
Is the account able to spend?	Billing
Is the key enabled and scoped correctly?	API Keys
Is the model available in the public catalog?	Models
What does the error code mean?	Error handling

Fast triage

Test GET /v1/models with the same key.
Check whether the failing request appears in Usage Logs.
If it appears, copy the request ID, result status, model ID, latency, and error code.
Try one small non-streaming request with a known fast model.
Check Status for NexoRouter gateway and model gateway availability.
If only one model fails, switch model temporarily and include both model IDs in the support note.

Decision table

Observation	Likely area	Next action
`GET /v1/models` fails with the same key	Key, account, or gateway	Check API Keys, Billing, and Status.
Request never appears in Usage Logs	Client, network, base URL, or wrong provider config	Confirm base URL, proxy, and tool provider selection.
Usage Logs shows `invalid_api_key`	Key or auth header	Follow API key invalid.
Usage Logs shows `model_not_found`	Model ID or key model scope	Copy model ID from Models and check the key scope.
Usage Logs shows quota/balance error	Billing or key budget	Check Billing and create a replacement key if the key budget is too low.
One model fails but another works	Model-specific upstream or model routing	Use the working model temporarily and report both model IDs.
All models time out from one network	Client network, proxy, firewall, or region	Try another network or server and review Network/proxy.

Known-safe test request

Use a small non-streaming request while debugging:

curl https://api.nexorouter.com/v1/chat/completions \
  -H "Authorization: Bearer $NEXOROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [
      { "role": "user", "content": "Reply with: ok" }
    ],
    "max_tokens": 16
  }'

If this succeeds but your app still fails, the issue is likely in app configuration, request size, streaming, tool calling, proxy behavior, or model choice.

What to include in support

Request ID:
Model ID:
Endpoint:
Usage Logs status:
Client HTTP status, if available:
Error code:
Approximate time:
Client/tool:
Whether /v1/models works:
Whether a small non-streaming request works:

Do not include the full API key. If a key may have leaked, revoke it and create a new one before sharing diagnostics.

What not to infer

Status can show NexoRouter availability, but it does not prove every upstream model is healthy.
A successful text request does not prove streaming or tool calling works for that model.
A model missing from your key scope is not the same as a model being unavailable globally.
A client timeout is not always a gateway outage.