StreamLake
Explore StreamLake models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
StreamLakestreamlake
No provider claimThese privacy labels describe StreamLake, the upstream model provider. ZDR is a retention policy; verified confidential inference additionally requires attested provider compute and end-to-end encryption.
| Provider | StreamLake |
|---|---|
| Routing status | Active |
| Provider website | https://www.streamlake.ai/ |
| Models | 3 public models |
| Credits routes | 3 |
| Zero data retention | not claimed |
| Verified confidential inference | Not verified |
| Policy note | No provider-ZDR claim is tracked. StreamLake's public privacy policy is linked for API data-handling review. Policy source |
Models served by StreamLake.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
kwaipilot/kat-coder-air-v2.5KAT Coder Air V2.5 |
— | 262,144 | $0.15825/1M | $0.03165/1M | $0.633/1M |
kwaipilot/kat-coder-pro-v2KAT Coder Pro V2 |
— | 262,144 | $0.3165/1M | $0.0633/1M | $1.266/1M |
kwaipilot/kat-coder-pro-v2.5KAT Coder Pro V2.5 |
— | 262,144 | $0.7807/1M | $0.15825/1M | $3.1228/1M |
Questions
Does StreamLake have zero data retention?
TrustedRouter does not currently mark StreamLake as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is StreamLake end-to-end encrypted?
TrustedRouter does not currently mark StreamLake as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which StreamLake models are available through TrustedRouter?
This page currently lists 3 public StreamLake models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.