Groq 429: read the RPM/TPM/RPD dimension and honor retry-after

TL;DR

'Rate limit reached for model llama-3.3-70b-versatile on tokens per minute (TPM): Limit 6000, Used 5800, Requested 500' tells you the dimension.

Fix

1. 'Rate limit reached for model llama-3.3-70b-versatile on tokens per minute (TPM): Limit 6000, Used 5800, Requested 500' tells you the dimension. Expected: you can confirm this matches your situation.

When to use

• You are setting up or using this Groq 429 feature.
• The symptom matches: read the RPM/TPM/RPD dimension and honor retry-after.

When NOT to use

• Unrelated Groq 429 issues (different feature, different failure).
• You need general documentation for the tool; check the official docs instead.

Compatibility

Reported against Groq 429 (mentions 3.3). Source: https://github.com/funxgao/claude-code-plugins-plus-skills/blob/HEAD/plugins/saas-packs/groq-pack/skills/groq-common-err.

Variant phrasings

read the RPM/TPM/RPD dimension and honor retry-after

Why it happens

Groq's 429 names the exact dimension you hit. The fix depends on which one.

Edge cases

• If your error message differs even slightly, this is probably a different issue; search the exact text.
• Behavior can change between releases; the linked source reflects the versions above.
• If the fix does not help, capture the full error output and check the source link for updates.

Source

https://github.com/funxgao/claude-code-plugins-plus-skills/blob/HEAD/plugins/saas-packs/groq-pack/skills/groq-common-errors/SKILL.md

Source: Groq's 429 names the exact dimension you hit. The fix depends on which one.

Verified resolution: [groq-common-errors skill]: 'Rate limit reached for model llama-3.3-70b-versatile on tokens per minute (TPM): Limit 6000, Used 5800, Requested 500' tells you the dimension. Groq returns retry-after plus x-ratelimit-limit-requests, x-ratelimit-limit-tokens, x-ratelimit-remaining-requests/tokens, and x-ratelimit-reset-requests/tokens headers. Read retry-after and back off once; hammering resets nothing. TPM exhaustion from one oversized request is not a ban: reduce the message size and retry.

Source URL: https://github.com/funxgao/claude-code-plugins-plus-skills/blob/HEAD/plugins/saas-packs/groq-pack/skills/groq-common-errors/SKILL.md