Errors

All errors return OpenAI-shaped JSON:

{ "error": { "message": "...", "type": "...", "code": "..." } }

HTTP	`code`	`type`	Retryable	What to do
400	`missing_model`	`invalid_request_error`	no	Add `"model"` to the body or use a prompt that pins one.
400	`unknown_model`	`invalid_request_error`	no	Slug not in catalog. See platform models list.
503	`vendor_unavailable`	`service_unavailable`	wait	A dependency inside odnoga is failing. The message is deliberately generic and never carries the provider's own text: a supplier-account problem is ours, not yours. `x-odnoga-ticket` carries the ticket already open with the odnoga team at highest priority. Retry shortly or send another model.
400	`model_deprecated`	`invalid_request_error`	no	The model is retired. The message names the retirement date and the replacement; move to it. An organisation admin can instead enable Organisation → Defaults → Retired models so the same-vendor replacement serves the old name automatically (the response then carries `x-odnoga-model-fallback`).
400	`model_not_allowed`	`invalid_request_error`	no	Workspace allowlist rejected this model. Add it under Routing → Allowed models.
400	`missing_messages`	`invalid_request_error`	no	Send `messages` (or `prompt`).
400	`invalid_prompt`	`invalid_request_error`	no	Prompt slug not found or label/version mismatch.
401	`invalid_api_key`	`authentication_error`	no	Wrong / revoked virtual key. Mint a new one.
402	`budget_exhausted`	`billing_error`	wait	Active budget window is full. Wait for reset or raise cap.
402	`end_user_exhausted`	`billing_error`	no	That end user's wallet is empty. Nothing was sent to a vendor and nothing was charged. Expected, not an incident — catch it and show your own top-up or upgrade screen. The message names the unit you configured. Credit the wallet with `wallets.adjust`, or turn off "block at zero" to meter without enforcing.
402	`subscription_inactive`	`billing_error`	no	Workspace billing canceled/unpaid. Fix in Pay odnoga.
402	`no_vendor_key`	`billing_error`	no	No vault key for that vendor. Add one in Routing → Vault keys.
429	`rate_limited`	`rate_limit_error`	yes (backoff)	Honor `x-ratelimit-reset`. Exponential backoff.
502	`upstream_error`	`api_error`	yes	Vendor returned an error. Check Request Inspector.
504	`timeout`	`api_error`	yes	Vendor didn't respond in time. Retry with backoff.
500	`internal`	`api_error`	yes	Open a ticket with the `x-airouter-request-id`.

Retry policy (consumer)

Never retry 4xx other than 429 and 408.
Retry with exponential backoff for 429, 5xx, network errors. Cap at 3 attempts.
Always respect x-ratelimit-reset when present.

See Retries and timeouts for a tested helper.