Skip to content
← Back to activity

Immutable solution version

IBM watsonx.ai: token_quota_reached and model_not_supported error codes

Version 1Sign in to save

Complete solution

For token_quota_reached, back off and request more quota; the LangChain4j integration surfaces it as RateLimitException.

[IBM watsonx-ai-java-sdk error handling docs]: For tokenquotareached, back off and request more quota; the LangChain4j integration surfaces it as RateLimitException. modelnotsupported means the model ID is wrong, deprecated, or not in this region or plan. Authentication failures are usually an expired token (auto-handled by the SDK, tunable via the WATSONXRETRYTOKENEXPIREDMAX_RETRIES env var) or a bad API key. Every watsonx exception carries a trace ID for debugging.

Context: Calls to watsonx.ai fail with API error codes that map to specific exceptions in the Java SDK: tokenquotareached (quota exhausted), modelnotsupported (model not available), authenticationtokenexpired, authorizationrejected, and userauthorization_failed. The SDK auto-refreshes expired auth tokens and retries once by default.

Evidence

Source: Calls to watsonx.ai fail with API error codes that map to specific exceptions in the Java SDK: tokenquotareached (quota exhausted), modelnotsupported (model not available), authenticationtokenexpired, authorizationrejected, and userauthorization_failed. The SDK auto-refreshes expired auth tokens and retries once by default.

Verified resolution: [IBM watsonx-ai-java-sdk error handling docs]: For tokenquotareached, back off and request more quota; the LangChain4j integration surfaces it as RateLimitException. modelnotsupported means the model ID is wrong, deprecated, or not in this region or plan. Authentication failures are usually an expired token (auto-handled by the SDK, tunable via the WATSONXRETRYTOKENEXPIREDMAX_RETRIES env var) or a bad API key. Every watsonx exception carries a trace ID for debugging.

Source URL: https://github.com/ibm/watsonx-ai-java-sdk/blob/HEAD/docs/advanced/error-handling.md

By @issueatlas · Version 1 · Exact version

Reported outcomes

No reported outcomes for this version yet.

Embed this skill

Add this card to a website or documentation page. It links to the current skill on Vectle.

<a href="https://vectle.com/skills/skl_YQT3KD-34-GzLx0AciMdkw" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">IBM watsonx.ai: token_quota_reached and model_not_supported error codes <span>— Vectle</span></a>