Same meaning. Roughly half the tokens.
The compression engine rewrites prompts and tool output into a denser stream models understand natively — lossless-first by default, aggressive on request.
How the gateway folds a prompt.
A set of transforms run in a single pass, inline, before the request is billed. Meaning is preserved — not every byte.
-
01
Stale-read supersession−18%
Older copies of a re-read file are dropped; the newest read stays verbatim.
-
02
Context compaction−22%
Stale turns and dead tool output folded out losslessly.
-
03
Cross-turn dedup−9%
Repeated instructions and echoed tool results collapsed across turns.
-
04
Structural rewrite−4%
Whitespace, JSON and markup normalised to a dense form.
Illustrative per-transform split on a blended coding workload — your mix may vary.
Each fold, explained.
Every transform runs inline in the gateway — no round trips, no external calls.
Stale-read supersession
When an agent re-reads a file after editing it, the older copy is dropped and only the newest read is kept verbatim — the model sees the current state, not the history of reads.
Context compaction
Stale conversation turns and dead tool output are folded out losslessly — the model keeps the gist, drops the bytes.
Cross-turn dedup
Repeated instructions and echoed tool results are collapsed across turns — the same content isn't re-sent at full size every time.
Structural rewrite
Whitespace, JSON indentation and markup are normalised to a dense form the tokenizer handles in fewer tokens.
Meaning is preserved,
not every byte.
The gateway favours lossless transforms — folding out stale reads, dead tool output and repeated spans — so the model keeps the gist without the redundant bytes. Nothing the agent needs is dropped irrecoverably.
- ✓Lossless-first. Stale and repeated content is folded; the newest working set stays verbatim.
- ✓Per-request receipt. Tokens saved, percentage and dollar impact — visible in the dashboard.
- ✓Inline in the gateway. No round trips, no external calls.
Input tokens cut roughly in half on a blended enterprise workload.
Every request comes with a receipt.
Tokens saved, percentage and dollar impact — visible per request in the dashboard, exportable to your SIEM.
2,171 tokens kept in your budget.
Compression runs inline in the gateway — no round trips, no external calls.
Input tokens cut roughly in half on a blended enterprise workload.
Stale and repeated content folded; the newest working set stays verbatim.
Send fewer tokens. Keep the answers.
Compression starts on request one — no config, no model change, no migration.