# Celeris-1 Decision vs GLiClass

> GLiClass and Celeris-1 Decision score within a point of each other on agent readiness, 49.9 (D) and 49.3 (D). Celeris-1 Decision leads on schema & documentation, agent ergonomics and security & auth. Both do inference decision. Celeris-1 Decision is cheaper for inference…

- Canonical: https://www.anchorterminal.com/compare/celeris-1-decision-vs-gliclass
- Markdown: https://www.anchorterminal.com/compare/celeris-1-decision-vs-gliclass.md (~2,450 tokens)
- Slim: https://www.anchorterminal.com/compare/celeris-1-decision-vs-gliclass.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/celeris-1-decision-vs-gliclass.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

GLiClass and Celeris-1 Decision score within a point of each other on agent readiness, 49.9 (D) and 49.3 (D). Celeris-1 Decision leads on schema & documentation, agent ergonomics and security & auth. Both do inference decision. Celeris-1 Decision is cheaper for inference decision, $0 against $0 per 1M tokens.

- Celeris-1 Decision: grade D, 49.3/100, rank #708 of 842. Markdown https://www.anchorterminal.com/tools/celeris-1-decision.md · JSON https://www.anchorterminal.com/api/v1/tools/celeris-1-decision.json
- 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

## Which one, for what

### Celeris-1 Decision (D)

Good for: Multimodal classification, routing and bounded decisions with probabilities and optional explanations

Ahead on:
- Schema & documentation, 60 against 49
- Agent ergonomics, 80 against 60
- Security & auth, 45 against 38

Also in its favour:
- Cheaper for inference decision, $0 against $0 per 1M tokens
- A hosted endpoint, with nothing to install

Watch for: Early-access terms and capacity-dependent workspace activation

### 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:
- Payments & pricing, 60 against 20
- Transparency & trust, 64 against 53

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


## Score by category

| Category | Weight | Celeris-1 Decision | GLiClass | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 40 | 43 | GLiClass +3 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 60 | 49 | Celeris-1 Decision +11 |
| Agent ergonomics | 13% (16.2 this run) | 80 | 60 | Celeris-1 Decision +20 |
| Security & auth | 14% (17.5 this run) | 45 | 38 | Celeris-1 Decision +7 |
| Payments & pricing | 10% (12.5 this run) | 20 | 60 | GLiClass +40 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 40 | 44 | GLiClass +4 |
| Transparency & trust | 7% (8.8 this run) | 53 | 64 | GLiClass +11 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **49.3 · D** | **49.9 · D** | |

## Facts side by side

| Fact | Celeris-1 Decision | GLiClass |
| --- | --- | --- |
| Kind | Model API | Model API |
| Vendor | Celeris (Marqo Inc) | Knowledgator |
| Hosted endpoint | `https://inference.celeris.ai/celeris-1-decision/v1/systemone` | no (local only) |
| Transports | HTTP | HTTP |
| Auth | API key | None |
| Pricing | Pay per use | Free |
| Price for inference decision | free | free |
| x402 | no | no |
| Licence | Proprietary hosted model under Celeris terms of service | Apache-2.0 (library and the model weights we checked) |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-10-08 | 2026-07-21 |
| Terms last updated | 2026-09-08 | no document linked |
| Privacy policy last updated | 2026-07-23 | no document linked |
| Customer content may train models | not found in the text |  |
| Terms restrict automated access | not found in the text |  |
| Terms restrict benchmarking | yes |  |
| Terms or service can change without notice | not found in the text |  |
| Arbitration or class-action waiver | not found in the text |  |
| Popularity | none | 555 stars, 13k PyPI/wk |

## Verdicts

**Celeris-1 Decision.** Typed probabilities, image inputs and optional explanations suit routing and classification inside an agent. Both System One and OpenAI Decisions request formats are documented. The service remains early access under its terms, activation can queue, and prepaid credit expires after 30 days. The published accuracy and latency figures are Celeris measurements, not Anchor Terminal tests.

**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.

## Before you call either

### Celeris-1 Decision

1. Use the decision model path and matching model field. This model has no chat, Responses or models endpoint.
2. Use at most 512 questions per request, or 64 with explanations. Both endpoints reject streaming.
3. Preserve x_celeris in a custom Jev SDK response model when reading explanations. The default response type drops it.
4. Retry 429 with Retry-After and backoff. Stop on 402 until workspace credit is replenished.
5. Read usage.input_tokens for cost, including images and request overhead. Track credit expiry separately from token consumption.

### 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

## Questions

### Which is better for AI agents, Celeris-1 Decision or GLiClass?

GLiClass and Celeris-1 Decision score within a point of each other on agent readiness, 49.9 (D) and 49.3 (D). Celeris-1 Decision leads on schema & documentation, agent ergonomics and security & auth.

### Which is cheaper for inference decision, Celeris-1 Decision or GLiClass?

Celeris-1 Decision, at free against free for GLiClass. These are the vendors' published prices for the job.

### Do Celeris-1 Decision and GLiClass need an API key?

Celeris-1 Decision needs an API key. GLiClass needs no key.

### Can an agent call Celeris-1 Decision and GLiClass without installing anything?

Celeris-1 Decision has a hosted endpoint at https://inference.celeris.ai/celeris-1-decision/v1/systemone. No hosted endpoint is listed for GLiClass.

### Are Celeris-1 Decision and GLiClass open source?

No open-source release is listed for Celeris-1 Decision. GLiClass is open source (Apache-2.0 (library and the model weights we checked)).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/celeris-1-decision-vs-gliclass.json, and with the fewest tokens: https://www.anchorterminal.com/compare/celeris-1-decision-vs-gliclass.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "celeris-1-decision", "b": "gliclass"}`. From a terminal: `anchor compare celeris-1-decision gliclass`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/celeris-1-decision.json and https://www.anchorterminal.com/api/v1/tools/gliclass.json

## Other comparisons with Celeris-1 Decision or GLiClass

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