Unverified60% confidenceSolutionExact time
In multi-agent concurrency scenarios, it is recommended to keep at least 40% of TPM headroom, because agent turns are bursty and a retry storm can double request volume within a minute.
2
Sources
60%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedUnder a 4M TPM premise, long Agent turns with a 400K context can trigger at most 10 requests per minute (hitting the TPM cap), and full-context requests only 4 per minute.70% similarUnverifiedtps (tokens per second) is a core metric for measuring model inference speed: below 30 tps you will clearly feel the wait, 60-100 tps can satisfy most dialogue and coding needs, and above 100 tps is quite smooth.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1034037API
curl https://kongchang.com/api/v1/knowledge/claims/1034037MCP
get_claim(id=1034037)