Errors and Support¶
What an Error Looks Like¶
If Nexus rejects a request, the response contains:
messagetypecoderequest_id
For support, request_id is the most important field.
Common Errors¶
invalid_key¶
The key is missing, incorrect, disabled, or revoked.
Check:
- the
Authorization: Bearer <API_KEY>header; - the
x-api-keyheader, if your client uses it; - that there are no extra spaces.
endpoint_not_allowed¶
Your key does not have access to the selected endpoint.
Make sure the client is configured for the intended workflow. If you need different access, contact support.
model_not_allowed¶
The model is not enabled for your key.
Run GET /v1/models and choose a model from the response.
unsupported_model¶
The model does not work on the selected endpoint.
For example, a model may be available for chat.completions but not for responses.
unsupported_endpoint¶
The client sent a request to an unsupported endpoint.
Use only the endpoints listed on the Supported Endpoints page.
streaming_not_supported¶
The client requested streaming where Nexus does not support it.
Streaming is supported for:
POST /v1/messages;POST /v1/responses;POST /v1/responses/compact.
missing_model¶
The request body does not include the model field.
Add the model to the JSON request.
insufficient_balance¶
The key does not have enough funds for the new request or for its temporary reserve.
Top up the balance and try again.
pricing_unavailable¶
Safe pricing calculation is temporarily unavailable for the selected model.
This is usually resolved on the support side. Try again later or contact support with the request_id.
pricing_stale¶
The pricing entry for the model needs to be refreshed before a new request can be accepted.
Try again later or contact support.
duplicate_request_id¶
This x-request-id has already been accepted earlier.
Create a new x-request-id, or remove this header if your client does not require it.
billing_finalization_failed¶
The request reached the final billing stage, but automatic finalization failed.
Send the request_id to support. Do not retry immediately until it is clear whether the response was already accounted for.
Service Request Error¶
The request did not complete successfully.
Try again later. If the issue repeats, send support the model, endpoint, time of the error, and request_id.
internal_error¶
Internal service error.
Send the request_id to support.
When to Contact Support¶
Contact support if:
- the key is active, but models do not appear;
- the balance was topped up, but requests are still rejected;
- the same error keeps repeating;
- you need an additional API key;
- you need a manual billing review.
Contact:
- Bot with support
- direct messages on the marketplace
What to Include¶
request_id;- model;
- endpoint;
- approximate time of the error;
- client or tool name.