ScaleDown
Try ScaleDown on us. Starter credit covers your first requests, then one key reaches all 4 ScaleDown models, with the privacy posture shown on every route.
ScaleDownscaledown
These privacy labels describe ScaleDown, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.
| Provider | ScaleDown |
|---|---|
| API operator country | US Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Not verified |
| Routing status | Active |
| Provider website | https://scaledown.ai/ |
| Models | 4 public models |
| Credits routes | 4 |
| Zero data retention | yes All routes |
| Verified confidential inference | Not verified |
| Policy note | Carbon ScaleDown, Inc. serves compression, summarization, extraction, and classification tasks. Its public DPA commits to volatile-memory processing, zero retention of customer inputs and outputs, no model training on customer data, and US-only processing. Content-free operational logs may be retained for up to 90 days. These are ZDR routes, not attested confidential-compute or E2EE routes. Input tokens are billable; output tokens are free. Policy source |
Inference locations
Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.
usage.provider_usage.gateway_region identifies the TrustedRouter gateway, not the provider's inference location. A value such as europe-west4 does not mean the model ran in Europe. usage.inference_location.serving_region remains null when the provider has not reported it. Older gateways may return the gateway-only field as provider_usage.region.
Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.
- Declared countries or regions
- United States
ScaleDown's marketplace application states that hosted processing occurs in the US and requires written consent for processing elsewhere. Customer-run VPC deployments are separate. - Can locations change?
- Individual US sites and model placement are unspecified; confirm the applicable contract before relying on residency.
- Provider region pinning
- No per-request regional pin verified.
- Pinning through TrustedRouter
- Not supported by the current TrustedRouter integration.
- Infrastructure declaration
- US hosted processing, provider-submitted declaration; individual site unspecified.
- Evidence
- Provider-submitted marketplace information; linked DPA for contractual review. Reviewed .
Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.
Measured performance
26 samplesContinuously sampled across ScaleDown's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 1121 ms |
|---|---|
| Effective throughput | — |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| scaledown/classify | 982 ms | — | 100.00% | — | 7 |
| scaledown/extract | 1121 ms | — | 100.00% | — | 6 |
| scaledown/compress | 1139 ms | — | 100.00% | — | 9 |
| scaledown/summarize | 1220 ms | — | 100.00% | — | 4 |
ScaleDown performance history · Full provider & model leaderboard.
Models served by ScaleDown.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
scaledown/classifyScaleDown Classify |
— | 1,000,000 | $0.05275/1M | Not published | $0/1M |
scaledown/compressScaleDown Compress |
— | 1,000,000 | $0.05275/1M | Not published | $0/1M |
scaledown/extractScaleDown Extract |
— | 1,000,000 | $0.05275/1M | Not published | $0/1M |
scaledown/summarizeScaleDown Summarize |
— | 1,000,000 | $0.05275/1M | Not published | $0/1M |
Questions
Does ScaleDown have zero data retention?
TrustedRouter records ScaleDown as supporting provider-level zero data retention based on the policy source linked on this page. This is a provider policy claim, separate from TrustedRouter's content-stateless real-time gateway and from end-to-end confidential compute.
Is ScaleDown end-to-end encrypted?
TrustedRouter does not currently mark ScaleDown 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 ScaleDown models are available through TrustedRouter?
This page currently lists 4 public ScaleDown models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.