litellm

14 Commits 2 Branches 0 Tags

1 Commits

Author	SHA1	Message	Date
inference-bot	576885ed21	Fix Tinfoil spend gap: raise timeout 30->180s, num_retries 2->0 DeepSeek V4.1 Flash is a reasoning model; 30s timeout caused LiteLLM to abandon in-flight generations (falling back to GPT-OSS) while Tinfoil still completed and billed them. num_retries re-hit Tinfoil up to 3x. Result: Tinfoil billed ~2x the tokens LiteLLM logged. Generous timeout + zero retries stops the silent re-billing.	2026-09-22 18:05:27 -06:00

Author

SHA1

Message

Date

inference-bot

576885ed21

Fix Tinfoil spend gap: raise timeout 30->180s, num_retries 2->0

DeepSeek V4.1 Flash is a reasoning model; 30s timeout caused LiteLLM to
abandon in-flight generations (falling back to GPT-OSS) while Tinfoil still
completed and billed them. num_retries re-hit Tinfoil up to 3x. Result: Tinfoil
billed ~2x the tokens LiteLLM logged. Generous timeout + zero retries stops
the silent re-billing.

2026-09-22 18:05:27 -06:00