# GLiClass vs ScaleDown

> GLiClass scores 49.9 (D) to ScaleDown's 48.6 (D) for decision models. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/gliclass-vs-scaledown
- Markdown: https://www.anchorterminal.com/compare/gliclass-vs-scaledown.md (~2,750 tokens)
- Slim: https://www.anchorterminal.com/compare/gliclass-vs-scaledown.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/gliclass-vs-scaledown.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Licence: CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.
- Updated: 2026-10-15

GLiClass scores 49.9 (D) on agent readiness against ScaleDown's 48.6 (D), and leads in 3 of 7 scored categories. ScaleDown leads on schema & documentation, agent ergonomics, security & auth and maintenance & community. Both do decision models.

- GLiClass: grade D, 49.9/100, rank #848 of 1094. Markdown https://www.anchorterminal.com/tools/gliclass.md · JSON https://www.anchorterminal.com/api/v1/tools/gliclass.json
- ScaleDown: grade D, 48.6/100, rank #880 of 1094. Markdown https://www.anchorterminal.com/tools/scaledown.md · JSON https://www.anchorterminal.com/api/v1/tools/scaledown.json
- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md
- All 136 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md
- Best document parsing, OCR and extraction APIs for AI agents: https://www.anchorterminal.com/best/document-extraction/index.md
- All 125 documents comparisons: https://www.anchorterminal.com/compare/document-extraction/index.md

## Which one, for what

### GLiClass (D)

Good for: Topic, intent and sentiment routing over a known label set on the owner's own CPU or GPU, where many labels must be scored at once.

Ahead on:
- Reliability, 43 against 20
- Payments & pricing, 60 against 40
- Transparency & trust, 64 against 54

Also in its favour:
- No key needed to call it
- Open source

Watch for: No calibration evidence. The cards report F1 only, and the docs tell users to calibrate thresholds on their own traffic

### ScaleDown (D)

Good for: Cheap, high-volume labelling, routing and yes or no checks where a probability is more useful than prose, and for pulling described fields with offsets from text, images or PDFs.

Ahead on:
- Schema & documentation, 69 against 49
- Agent ergonomics, 76 against 60
- Security & auth, 48 against 38
- Maintenance & community, 56 against 44

Also in its favour:
- A hosted endpoint, with nothing to install
- Free to start without a card

Watch for: No status page, no published rate limits and no SLA outside enterprise contracts


## Score by category

| Category | Weight | GLiClass | ScaleDown | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 43 | 20 | GLiClass +23 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 49 | 69 | ScaleDown +20 |
| Agent ergonomics | 13% (16.2 this run) | 60 | 76 | ScaleDown +16 |
| Security & auth | 14% (17.5 this run) | 38 | 48 | ScaleDown +10 |
| Payments & pricing | 10% (12.5 this run) | 60 | 40 | GLiClass +20 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 44 | 56 | ScaleDown +12 |
| Transparency & trust | 7% (8.8 this run) | 64 | 54 | GLiClass +10 |
| Negative events | ≤15 | 0 | -2 | |
| **Total** | | **49.9 · D** | **48.6 · D** | |

## Facts side by side

| Fact | GLiClass | ScaleDown |
| --- | --- | --- |
| Kind | Model API | Model API |
| Vendor | Knowledgator | Carbon ScaleDown, Inc. |
| Hosted endpoint | no (local only) | `https://api.scaledown.xyz` |
| Transports | HTTP | HTTP |
| Auth | None | API key |
| Pricing | Free | Pay per use |
| x402 | no | no |
| Licence | Apache-2.0 (library and the model weights we checked) | Proprietary hosted models under ScaleDown's Terms of Service. The langchain-scaledown integration is MIT |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-07-21 | 2026-10-14 |
| Terms last updated | no document linked | couldn't be read |
| Privacy policy last updated | no document linked | couldn't be read |
| Customer content may train models |  | couldn't be read |
| Terms restrict automated access |  | couldn't be read |
| Terms restrict benchmarking |  | couldn't be read |
| Terms or service can change without notice |  | couldn't be read |
| Arbitration or class-action waiver |  | couldn't be read |
| Popularity | 555 stars, 13k PyPI/wk | 0 stars |

## Verdicts

**GLiClass.** An Apache-2.0 classifier that scores a whole label set in one encoder pass on the owner's hardware, with single-label, multi-label, hierarchical and few-shot modes. It returns label scores with no calibration claim, the bundled server has no authentication, and the last three test runs on the main branch, on 24 September 2026, failed.

**ScaleDown.** 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.

## Before you call either

### GLiClass

1. Pass `--host 127.0.0.1` to `python -m gliclass.serve`, or put the port behind your own gateway. The server checks no credential
2. On a machine without a GPU add `--device cpu --dtype float32 --num-gpus-per-replica 0`. The default configuration expects CUDA
3. Send one text a request to `POST /gliclass`. An array in `texts` is cut to its first item without an error
4. Set `multi_label` to false for one label from a set. The default scores each label independently, so scores do not sum to 1
5. Keep text plus labels under the pipeline's 1,024-token `max_length`, or use `ZeroShotClassificationWithChunkingPipeline`. Longer input is truncated silently

### ScaleDown

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

## Questions

### Which is better for AI agents, GLiClass or ScaleDown?

GLiClass scores 49.9 (D) on agent readiness against ScaleDown's 48.6 (D), and leads in 3 of 7 scored categories. ScaleDown leads on schema & documentation, agent ergonomics, security & auth and maintenance & community.

### Do GLiClass and ScaleDown need an API key?

GLiClass needs no key. ScaleDown needs an API key.

### Can an agent call GLiClass and ScaleDown without installing anything?

No hosted endpoint is listed for GLiClass. ScaleDown has a hosted endpoint at https://api.scaledown.xyz.

### Are GLiClass and ScaleDown open source?

GLiClass is open source (Apache-2.0 (library and the model weights we checked)). No open-source release is listed for ScaleDown.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/gliclass-vs-scaledown.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gliclass-vs-scaledown.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "gliclass", "b": "scaledown"}`. From a terminal: `anchor compare gliclass scaledown`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gliclass.json and https://www.anchorterminal.com/api/v1/tools/scaledown.json

## Other comparisons with GLiClass or ScaleDown

- [Celeris-1 Decision vs GLiClass](https://www.anchorterminal.com/compare/celeris-1-decision-vs-gliclass.md)
- [Celeris-1 Decision vs ScaleDown](https://www.anchorterminal.com/compare/celeris-1-decision-vs-scaledown.md)
- [Clef vs GLiClass](https://www.anchorterminal.com/compare/cloudflare-clef-vs-gliclass.md)
- [Clef vs ScaleDown](https://www.anchorterminal.com/compare/cloudflare-clef-vs-scaledown.md)
- [Laya vs GLiClass](https://www.anchorterminal.com/compare/convai-laya-vs-gliclass.md)
- [Laya vs ScaleDown](https://www.anchorterminal.com/compare/convai-laya-vs-scaledown.md)
- [Decider vs GLiClass](https://www.anchorterminal.com/compare/decider-vs-gliclass.md)
- [Decider vs ScaleDown](https://www.anchorterminal.com/compare/decider-vs-scaledown.md)
- [Decision 3.0 vs GLiClass](https://www.anchorterminal.com/compare/decision-3-vs-gliclass.md)
- [Decision 3.0 vs ScaleDown](https://www.anchorterminal.com/compare/decision-3-vs-scaledown.md)
- [GLiClass vs Kev](https://www.anchorterminal.com/compare/gliclass-vs-jaredpalmer-kev.md)
- [GLiClass vs Liquid d1](https://www.anchorterminal.com/compare/gliclass-vs-liquid-d1.md)
- [GLiClass vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/gliclass-vs-microsoft-decision-1.md)
- [GLiClass vs Drex 1.5](https://www.anchorterminal.com/compare/gliclass-vs-nace-drex.md)
- [GLiClass vs OpenAI Decisions API](https://www.anchorterminal.com/compare/gliclass-vs-openai-decisions-api.md)
- [GLiClass vs pplx-decider](https://www.anchorterminal.com/compare/gliclass-vs-pplx-decider.md)
- [GLiClass vs SPEV](https://www.anchorterminal.com/compare/gliclass-vs-sprag-spev.md)
- [GLiClass vs Strands Decider 2B](https://www.anchorterminal.com/compare/gliclass-vs-strands-decider.md)
- [GLiClass vs Jev](https://www.anchorterminal.com/compare/gliclass-vs-typesafe-jev.md)
- [GLiClass vs Vela 2.0](https://www.anchorterminal.com/compare/gliclass-vs-vela.md)
- [Kev vs ScaleDown](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-scaledown.md)
- [Liquid d1 vs ScaleDown](https://www.anchorterminal.com/compare/liquid-d1-vs-scaledown.md)
- [Microsoft-Decision-1 vs ScaleDown](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-scaledown.md)
- [Drex 1.5 vs ScaleDown](https://www.anchorterminal.com/compare/nace-drex-vs-scaledown.md)
- [OpenAI Decisions API vs ScaleDown](https://www.anchorterminal.com/compare/openai-decisions-api-vs-scaledown.md)
- [pplx-decider vs ScaleDown](https://www.anchorterminal.com/compare/pplx-decider-vs-scaledown.md)
- [ScaleDown vs SPEV](https://www.anchorterminal.com/compare/scaledown-vs-sprag-spev.md)
- [ScaleDown vs Strands Decider 2B](https://www.anchorterminal.com/compare/scaledown-vs-strands-decider.md)
- [ScaleDown vs Jev](https://www.anchorterminal.com/compare/scaledown-vs-typesafe-jev.md)
- [ScaleDown vs Vela 2.0](https://www.anchorterminal.com/compare/scaledown-vs-vela.md)