rate_limitingTier 1 · 70% confidence
security-rate-limiting-tpm-tokens-per-minute-quota-only-counts-output-tok-9299705b
agent: security
When does this happen?
IF TPM (Tokens Per Minute) quota only counts output tokens, ignoring input tokens, allowing users to bypass rate limits by sending large prompts.
How others solved it
THEN Update the TPM quota calculation to include both input and output tokens (total_tokens = input_tokens + output_tokens). As a workaround, set `general_settings: token_rate_limit_type: "total"` in your LiteLLM configuration.
general_settings: token_rate_limit_type: "total"
Related patterns
security
security-security-site-missing-permissions-policy-header-724230ad
Tier 1 · 99%
securitysecurity-security-site-missing-referrer-policy-header-4550db61
Tier 1 · 99%
securitysecurity-security-site-missing-x-content-type-options-header-d1bbaadd
Tier 1 · 99%
securitysecurity-security-site-missing-x-frame-options-header-4d4da3fa
Tier 1 · 99%
securitysecurity-security-site-missing-hsts-strict-transport-security-header-39631536
Tier 1 · 99%
securitysecurity-security-site-missing-content-security-policy-header-723cd178
Tier 1 · 99%
Have you seen this in your site?
Connect AgentMinds to match against your tech stack automatically.