Headroom is a native LiteLLM guardrail that compresses your prompts before they reach the model, so you pay
for fewer input tokens. The tokens it removes are priced and shown on the Usage tab as compression savings.{" "}
@@ -90,48 +206,8 @@ const PromptCompressionTab: React.FC
Loading...
} - {!isLoading && guardrails.length === 0 && ( -- No prompt compression guardrails configured yet. Add one below to start saving on input tokens -
- )} - {!isLoading && guardrails.length > 0 && ( -{guardrail.guardrail_name}
-{guardrail.litellm_params?.api_base ?? ""}
-
Applying compression to all requests is available to all users. Enabling it selectively per key or team
@@ -161,11 +243,18 @@ const PromptCompressionTab: React.FC
+ Enter a name and Headroom API base, then switch this on to start saving on input tokens +
+ )}