# GLiClass vs Vela 2.0

> Vela 2.0 scores 66.5 (B) on agent readiness against GLiClass's 49.9 (D), and leads in 5 of 7 scored categories. GLiClass leads on transparency & trust. Both do inference decision. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/gliclass-vs-vela
- Markdown: https://www.anchorterminal.com/compare/gliclass-vs-vela.md (~2,250 tokens)
- Slim: https://www.anchorterminal.com/compare/gliclass-vs-vela.min.md (~530 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/gliclass-vs-vela.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
- Updated: 2026-10-09

Vela 2.0 scores 66.5 (B) on agent readiness against GLiClass's 49.9 (D), and leads in 5 of 7 scored categories. GLiClass leads on transparency & trust. Both do inference decision.

- GLiClass: grade D, 49.9/100, rank #697 of 842. Markdown https://www.anchorterminal.com/tools/gliclass.md · JSON https://www.anchorterminal.com/api/v1/tools/gliclass.json
- Vela 2.0: grade B, 66.5/100, rank #268 of 842. Markdown https://www.anchorterminal.com/tools/vela.md · JSON https://www.anchorterminal.com/api/v1/tools/vela.json

## 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:
- Transparency & trust, 64 against 48

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

### Vela 2.0 (B)

Good for: Self-hosted routing and guardrail checks in one call, where span offsets for personal data or unsupported claims matter.

Ahead on:
- Reliability, 57 against 43
- Schema & documentation, 78 against 49
- Agent ergonomics, 79 against 60
- Security & auth, 60 against 38
- Maintenance & community, 84 against 44

Watch for: No version tags on the four Hub repositories, and the 4B and 9B weights were replaced in place on 3 October 2026


## Score by category

| Category | Weight | GLiClass | Vela 2.0 | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 43 | 57 | Vela 2.0 +14 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 49 | 78 | Vela 2.0 +29 |
| Agent ergonomics | 13% (16.2 this run) | 60 | 79 | Vela 2.0 +19 |
| Security & auth | 14% (17.5 this run) | 38 | 60 | Vela 2.0 +22 |
| Payments & pricing | 10% (12.5 this run) | 60 | 60 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 44 | 84 | Vela 2.0 +40 |
| Transparency & trust | 7% (8.8 this run) | 64 | 48 | GLiClass +16 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **49.9 · D** | **66.5 · B** | |

## Facts side by side

| Fact | GLiClass | Vela 2.0 |
| --- | --- | --- |
| Kind | Model API | Model API |
| Vendor | Knowledgator | vLLM Semantic Router project and KR Labs |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | HTTP |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 (library and the model weights we checked) | Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-07-21 | 2026-10-06 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models |  |  |
| Terms restrict automated access |  |  |
| Terms restrict benchmarking |  |  |
| Terms or service can change without notice |  |  |
| Arbitration or class-action waiver |  |  |
| Popularity | 555 stars, 13k PyPI/wk | 6.1k 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.

**Vela 2.0.** One self-hosted call answers routing, prompt-attack, personal-data and unsupported-claim questions with probabilities and character offsets, under Apache-2.0 with SHA-256 manifests. The models are days old and carry no Hub version tags, and the three larger sizes keep 74 to 89 per cent of their Decision 2.0 bases on the Jev Decision Index by the authors' figures.

## 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

### Vela 2.0

1. Pin a commit hash with `revision=` when loading from the Hub. The repositories have no tags and `main` has changed since launch
2. Send the served name in `model`, for example `vllm-sr/Vela-2.0-4B`. The bundled server answers 422 to any other name
3. Name span questions `pii`, `halu` or `toxic`, or set `"head": "router"`, to get the trained router head. Other labels go to the broad head
4. Keep input under 16,384 tokens a sequence (8,192 on the 0.3B). The bundled server answers 413 when the questions alone don't fit
5. Set `VELA2_API_KEY` before binding the bundled server beyond 127.0.0.1, and keep the model runtime on a trusted network

## Questions

### Which is better for AI agents, GLiClass or Vela 2.0?

Vela 2.0 scores 66.5 (B) on agent readiness against GLiClass's 49.9 (D), and leads in 5 of 7 scored categories. GLiClass leads on transparency & trust.

### Do GLiClass and Vela 2.0 need an API key?

Neither needs a key.

### Can an agent call GLiClass and Vela 2.0 without installing anything?

No hosted endpoint is listed for GLiClass. No hosted endpoint is listed for Vela 2.0.

### Are GLiClass and Vela 2.0 open source?

Yes. GLiClass is open source (Apache-2.0 (library and the model weights we checked)). Vela 2.0 is open source (Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences).


## For agents

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

## Other comparisons with GLiClass or Vela 2.0

- [Celeris-1 Decision vs GLiClass](https://www.anchorterminal.com/compare/celeris-1-decision-vs-gliclass.md)
- [Celeris-1 Decision vs Vela 2.0](https://www.anchorterminal.com/compare/celeris-1-decision-vs-vela.md)
- [Clef vs GLiClass](https://www.anchorterminal.com/compare/cloudflare-clef-vs-gliclass.md)
- [Clef vs Vela 2.0](https://www.anchorterminal.com/compare/cloudflare-clef-vs-vela.md)
- [Laya vs GLiClass](https://www.anchorterminal.com/compare/convai-laya-vs-gliclass.md)
- [Laya vs Vela 2.0](https://www.anchorterminal.com/compare/convai-laya-vs-vela.md)
- [Decider vs GLiClass](https://www.anchorterminal.com/compare/decider-vs-gliclass.md)
- [Decider vs Vela 2.0](https://www.anchorterminal.com/compare/decider-vs-vela.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 OpenAI Decisions API](https://www.anchorterminal.com/compare/gliclass-vs-openai-decisions-api.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)
- [Kev vs Vela 2.0](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-vela.md)
- [Liquid d1 vs Vela 2.0](https://www.anchorterminal.com/compare/liquid-d1-vs-vela.md)
- [OpenAI Decisions API vs Vela 2.0](https://www.anchorterminal.com/compare/openai-decisions-api-vs-vela.md)
- [Strands Decider 2B vs Vela 2.0](https://www.anchorterminal.com/compare/strands-decider-vs-vela.md)
- [Jev vs Vela 2.0](https://www.anchorterminal.com/compare/typesafe-jev-vs-vela.md)