opusgate.
ModelsQuickstartPricing
Getting started
Overview
Setup guides
Claude CodeCodex CLICursorClineRoo CodeKilo CodeContinueOpenCode
API reference
Endpoints & authError codesRate limits
Account
API keysBilling & pricing
Reference
FAQTerms of ServicePrivacy Policy
opusgate.Opening your next page…
← PreviousEndpoints & authNext →Rate limits
opusgate.

AI models, one connection.
Build with your tools or start in chat.

Product

ModelsPricingWorkspacePayment methods

Get connected

Claude CodeCursorAPI referenceAll setup guides

Help

SupportFAQTermsPrivacy
© 2026 OpusGateModel and tool names belong to their respective owners.

Error codes

Two sources of errors: the OpusGate gateway itself (auth, connectivity — flat JSON bodies) and the upstream model provider (validation, balance, model errors — passed through verbatim in the Anthropic/OpenAI error format your SDK already understands).

Gateway errors

StatusBodyMeaningWhat to do
401{"error": "missing_api_key"}No key in the request.Send the key as Authorization: Bearer or x-api-key.
401{"error": "invalid_api_key"}Key unknown, revoked, or has stray whitespace.Re-paste the key; if in doubt, issue a fresh one on the Keys page.
403{"error": "account_frozen"}The account is suspended.Contact support@opusgate.dev.
429rate limit exceededA gateway request-rate or concurrency limit was reached.Respect Retry-After when supplied and reduce concurrency; see rate limits.
500{"error": "key_unavailable"}Internal key-storage error on our side.Not your fault — retry once, then contact support.
502{"error": "upstream_unreachable"}The gateway could not complete communication with the upstream provider.Keep the request ID and check usage before repeating a paid request whose result is uncertain.
504{"error": "upstream_timeout"}The gateway did not receive upstream response headers within its 300-second deadline.The upstream may still have processed the request. Check usage before retrying; a timeout does not prove that nothing was charged. For future requests, consider streaming or a smaller output limit.

Upstream errors (passed through)

These arrive in the provider's native shape, e.g. {"type": "error", "error": {"type": "...", "message": "..."}} for the Anthropic protocol. Review your SDK’s automatic retry policy for paid generation requests.

StatusTypeMeaningWhat to do
400invalid_request_errorMalformed body — bad parameter, missing max_tokens, oversized context.The error message names the field; fix the request.
402insufficient balanceYour credit balance can’t cover the request.Top up and retry — no reconfiguration needed.
404not_found_errorUnknown model ID.Copy the exact ID from the catalog — IDs are case-sensitive.
429rate_limit_errorUpstream throughput limit for your tier.Retry with exponential backoff.
500 / 529api_error / overloaded_errorThe model provider itself is erroring or overloaded.Retry with backoff, or switch models temporarily.
Before retrying a paid request
Correct validation and authentication errors before resubmitting. Respect rate-limit guidance. A timeout, disconnected stream or missing response can leave the billing outcome uncertain; OpusGate does not automatically repeat paid generation requests. Save any partial result and the request ID, check usage, and contact support@opusgate.dev if the outcome is unclear.