# ScaleDown (slim)

> ScaleDown's API serves three single-task Constrained Decoding Models (Classify, Extract and Summarize) and a Compress model, called with an API key at api.scaledown.xyz. Classify answers Jev-shaped decision requests with probabilities.

- Full: https://www.anchorterminal.com/tools/scaledown.md (~7,700 tokens) · this version ~1,630 tokens · JSON https://www.anchorterminal.com/tools/scaledown.json · canonical https://www.anchorterminal.com/tools/scaledown
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-15
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

**D · 48.6/100 · rank #881 of 1095 · #15 in Decision models · not agent-ready · confidence medium**


Assessment: Classify answers Jev-shaped `choice`, `noul` and `score` questions with probabilities, and Extract returns values with confidences and character offsets, at $0.05 per million input tokens with output free. There is no status page, no published rate limit and no public changelog, and the site's compliance claims contradict each other.

## Facts

- Kind: Model API · vendor: Carbon ScaleDown, Inc. · category: Decision models · legal entity: Carbon ScaleDown, Inc. · provenance 52/100
- Endpoint: `https://api.scaledown.xyz` (HTTP)
- Auth: API key · pricing: Pay per use · x402: no · licence: Proprietary hosted models under ScaleDown's Terms of Service. The langchain-scaledown integration is MIT
- Probe metrics: not measured yet (probes haven't run)
- Models: classify and classify-1 (Classify, also behind the Jev-shaped Decisions API), extract and extract-1, summarize and summarize-1, and compress. The bare names follow the latest version and the -1 names pin version 1
- Endpoints: POST /classify and POST /v1/scaledown for Classify, POST /v1/chat/completions for Extract and Summarize, POST /compress/raw/ for Compress, GET /v1/models
- Question types: choice (one option, probabilities sum to 1), noul (probability of yes), score (2 to 10 ordered levels, returned as an expected value). /classify takes up to 20 labels with rubrics, 16 in multi-label mode, and 50 chunks a request
- Extract output: Each value with a confidence, start and end character offsets and 500 characters of context each side by default, up to 30 values per type, plus nested objects and arrays
- Summarize output: At most 1,000 output tokens, with finish_reason length when cut off. Sampling parameters are fixed
- Context and inputs: 1M tokens for Summarize, Extract and Classify per the site FAQ and OpenRouter. Text, or base64 JPEG, PNG, TIFF and PDF documents
- Rate limits: Not published. The site says generous fair-use limits and the terms let ScaleDown change limits on reasonable notice
- Trains on API data: No, per the terms (6.3), the DPA and the site FAQ
- Data retention: Zero retention of request data per the DPA, with operational logs without customer data kept up to 90 days. Processing in the United States only
- Integrations: OpenRouter (Extract, Summarize), Vercel AI Gateway (Classify-1), LiteLLM, langchain-scaledown 0.2.0 and the LangSmith LLM Gateway
- Status page: None found
- Prices: Classify, Extract, Summarize and Compress input $0.05 per 1M tokens

- Scores: Reliability 20, Performance pending, Schema & documentation 69, Agent ergonomics 76, Security & auth 48, Payments & pricing 40, Task success pending, Maintenance & community 56, Transparency & trust 54 · negative events -2 · total over the 7 assessed categories
- Why: Reliability, Read as a hosted model API. · Schema & documentation, An OpenAPI 3.1 document (ScaleDown API 1.0.0) covers /compress/raw/, /classify and /v1/scaledown. · Agent ergonomics, Read as an API an agent calls for a decision, the reading used for Jev. · Security & auth, Read for a model API, on the lines used for Jev. · Payments & pricing, No x402, MPP or L402 on ScaleDown's endpoints or through the gateways that list it (0). · Maintenance & community, Read for a closed model, on the lines used for Jev. · Transparency & trust, Closed hosted models under published terms of service (20 July 2026), a privacy notice (3 June 2026) and a DPA, naming Carbon ScaleDown, Inc…
- Sources: 28, open questions: 8, both in the full twin
- Capabilities: inference.decision, docs.extract
- JSON: https://www.anchorterminal.com/api/v1/tools/scaledown.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/scaledown.svg` or a link to https://www.anchorterminal.com/tools/scaledown from a page on scaledown.ai or one of its subdomains, or the README of github.com/scaledown-team/langchain-scaledown, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Send several questions about one item in one `/v1/scaledown` call. Each becomes its own Classify call and the usage is summed
2. Pin `classify-1`, `extract-1` or `summarize-1` once you've tuned thresholds on your own labelled cases
3. Set `context_chars` to 0 and use `top_n` on Extract unless you need the 500 characters of context each side
4. Set `reasoning: false` on /classify when you only need the label. The reasoning call bills its input at 2x
5. Back off and retry on 429, 502 and 504. No limits are published and calls have no side effects

## Connect

```bash
pip install langchain-scaledown   # LangChain middleware; any OpenAI SDK also works against /v1/chat/completions
```

```bash
curl https://api.scaledown.xyz/v1/scaledown \
  -H "x-api-key: $SCALEDOWN_API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"classify-1","state":"I was charged twice for my subscription this month.","questions":{"category":{"type":"choice","criteria":{"billing":"About a charge, invoice, refund, or payment problem.","technical":"About a bug or something not working."}}}}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Google Cloud Document AI | BB | 73.9 | docs.extract | https://www.anchorterminal.com/tools/google-cloud-document-ai.min.md |
| Amazon Textract | BB | 73.5 | docs.extract | https://www.anchorterminal.com/tools/amazon-textract.min.md |
| OpenAI Decisions API | BB | 71.5 | inference.decision | https://www.anchorterminal.com/tools/openai-decisions-api.min.md |
| Decider | B | 69.5 | inference.decision | https://www.anchorterminal.com/tools/decider.min.md |
| Drex 1.5 | B | 69.5 | inference.decision | https://www.anchorterminal.com/tools/nace-drex.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)