llmcloud.ai
Features · Caching

Serve the answer, not the model.

Every request runs through cache-hit routing before it touches a provider. When a near-duplicate answer exists inside your workspace, we return it in under 100ms and skip the token bill entirely.

cache: "exact"

SHA of the normalized request. Zero false positives — same messages, same tools, same seed = same reply.

cache: "semantic"

Embedding cosine over the last user turn. Tunable threshold; defaults tuned per task class.

cache: "prefix"

Prefix-hashed system + tool schema. Skips the KV rebuild on providers that expose prefix caching.

Enable per request

POST /v1/chat/completions
{
  "model": "auto:cost",
  "messages": [...],
  "cache": { "mode": "semantic", "ttl": 3600, "threshold": 0.94 }
}

Responses include x-llmcloud-cache: hit|miss|stale and an x-llmcloud-cost-saved header so you can attribute savings in the usage dashboard.

workspace-scoped

Never bleed cached answers across orgs or users.

PII-aware

Redaction runs before the cache key is computed.

streamable

Cache hits stream back as SSE, same shape as a live completion.