OpenAI compatible API · Attested · Public status

ScaleDown Compress

Compare every TrustedRouter route for ScaleDown Compress, including token pricing, context limits, privacy policy, regional availability, measured uptime, and API support.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

`scaledown/compress`

US providers ScaleDown

All models

Publisher	ScaleDownscaledown
AI IQ	No AI IQ profile matched yet.
Context	1,000,000 tokens
Providers	ScaleDown
Credits routes	1 provider route
Modes	chat US providers
Billing	Credits

How to use ScaleDown Compress

Compress source text for a specific query. Input-only billing; no output-token charge.

Input	Send the native task JSON object as the content of one user message. Summarize also accepts plain text. Text only; tools, chat history, response_format, and image blocks are not supported by this adapter.
Output	A JSON object in choices[0].message.content, including native task results. Stream responses deliver the completed result together, not incremental upstream tokens. Usage reports the provider's billable input tokens; completion_tokens is zero.

Example input

{
  "context": "Acme launched Monday. Feedback will be reviewed Friday.",
  "prompt": "When will feedback be reviewed?",
  "scaledown": {
    "rate": "auto"
  }
}

Example output

{
  "results": {
    "compressed_prompt": "Feedback will be reviewed Friday."
  }
}

Current route evidence

Live leaderboard

$0.05275/1MLowest Credits input price

$0/1MLowest Credits output price

1380 msFastest measured p50 TTFT via scaledown

not enough dataHighest measured throughput

Recent provider-route uptime spans 100.00% across 1 route and 1 provider. Price comes from the current Credits catalog. Speed and uptime come from routed probes rather than vendor claims.

Providers serving this model

Sorted by lowest combined prompt and completion price. Use "provider": {"sort": "throughput"} in the request body (or append :nitro to the model id) to route to the fastest provider instead.

Trust boundary: TR router attestation verifies the TrustedRouter gateway only. Provider policy separately describes the upstream model host's retention, confidential compute, and E2EE posture.

Provider	Input	Cached input	Output	TR router attested	Provider policy
ScaleDownscaledown	$0.05275/1M	Not published	$0/1M	yes	ZDR provider E2EE not verified

Compare ScaleDown Compress

All comparisons

Qwen: Qwen3.8 27B vs ScaleDown Compress14 combined provider routes

Questions

What model ID should I use for ScaleDown Compress?

Use scaledown/compress as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.

Which providers serve ScaleDown Compress?

TrustedRouter currently lists ScaleDown for ScaleDown Compress. Provider availability and routing eligibility can change as catalog and health data update.

How much does ScaleDown Compress cost through TrustedRouter?

The current lowest Credits input price is $0.05275/1M and the lowest Credits output price is $0/1M. Prices are per one million tokens and come from the current route catalog.

How do I require zero data retention for ScaleDown Compress?

Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.