Rose 1 production benchmarks are liveView API docs
Rose workspace
Sign in to your compression workspace.
Manage API keys, run prompt compression tests, and see exactly how much context Rose removes before your model call.
Before the modelCompress retrieved context before OpenAI, Anthropic, or DeepSeek.
Usage receiptsTrack tokens saved, ratios, latency, and returned receipts.
Project keysIssue scoped bearer keys and revoke them when needed.
Safe spansKeep policies, schemas, and must-keep context intact.
- Project keys and revocation
- Playground runs with receipts
- Token savings by workspace
- Billing and usage limits