# GLiClass vs OpenAI Decisions API

> OpenAI Decisions API scores 71.5 (BB) on agent readiness against GLiClass's 49.9 (D), and leads in 6 of 7 scored categories. GLiClass leads on payments & pricing. Both do inference decision. Category scores, facts, verdicts and agent notes side by side.

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

OpenAI Decisions API scores 71.5 (BB) on agent readiness against GLiClass's 49.9 (D), and leads in 6 of 7 scored categories. GLiClass leads on payments & pricing. 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
- OpenAI Decisions API: grade BB, 71.5/100, rank #119 of 842. Markdown https://www.anchorterminal.com/tools/openai-decisions-api.md · JSON https://www.anchorterminal.com/api/v1/tools/openai-decisions-api.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:
- Payments & pricing, 60 against 30

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

### OpenAI Decisions API (BB)

Good for: High-volume yes or no checks, routing among fixed options and rubric scoring over text and images, for teams already on an OpenAI key.

Ahead on:
- Reliability, 53 against 43
- Schema & documentation, 89 against 49
- Agent ergonomics, 87 against 60
- Security & auth, 83 against 38
- Maintenance & community, 77 against 44
- Transparency & trust, 83 against 64

Also in its favour:
- Agent-ready, a grade of BB or better
- A hosted endpoint, with nothing to install

Watch for: Public beta released on 6 October 2026. The guide expects general availability in the coming weeks and gives no date


## Score by category

| Category | Weight | GLiClass | OpenAI Decisions API | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 43 | 53 | OpenAI Decisions API +10 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 49 | 89 | OpenAI Decisions API +40 |
| Agent ergonomics | 13% (16.2 this run) | 60 | 87 | OpenAI Decisions API +27 |
| Security & auth | 14% (17.5 this run) | 38 | 83 | OpenAI Decisions API +45 |
| Payments & pricing | 10% (12.5 this run) | 60 | 30 | GLiClass +30 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 44 | 77 | OpenAI Decisions API +33 |
| Transparency & trust | 7% (8.8 this run) | 64 | 83 | OpenAI Decisions API +19 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **49.9 · D** | **71.5 · BB** | |

## Facts side by side

| Fact | GLiClass | OpenAI Decisions API |
| --- | --- | --- |
| Kind | Model API | Model API |
| Vendor | Knowledgator | OpenAI |
| Hosted endpoint | no (local only) | `https://api.openai.com/v1/decisions` |
| Transports | HTTP | HTTP |
| Auth | None | API key |
| Pricing | Free | Pay per use |
| Price for inference decision | free | $0.10 per 1M tokens |
| x402 | no | no |
| Licence | Apache-2.0 (library and the model weights we checked) | Proprietary service under OpenAI's services agreement. The official SDKs are Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-07-21 | 2026-10-06 |
| 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 | 32k 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.

**OpenAI Decisions API.** Typed predicate, choice and score answers with probabilities, up to 200 questions a call, at $0.10 per million input tokens with no output charge. It is a public beta released on 6 October 2026, with one model alias, no dated snapshot, no Batch route and no SLA found.

## 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

### OpenAI Decisions API

1. Put independent questions about one input in a single `questions` array. Send a separate request when a question depends on an earlier answer
2. Check each answer's `type` before reading it. A question can come back as `refusal` while the others in the same request are answered
3. Encode images as base64 data URLs. Hosted URLs and `file_id` inputs are rejected
4. Give a `choice` question a fallback value such as `other`, and set thresholds from your own labelled examples
5. Use Python SDK 3.26.0 or JavaScript 7.30.0 or later, and follow `Retry-After` on 429 and 503

## Questions

### Which is better for AI agents, GLiClass or OpenAI Decisions API?

OpenAI Decisions API scores 71.5 (BB) on agent readiness against GLiClass's 49.9 (D), and leads in 6 of 7 scored categories. GLiClass leads on payments & pricing.

### Which is cheaper for inference decision, GLiClass or OpenAI Decisions API?

GLiClass, at free against $0.10 per 1M tokens for OpenAI Decisions API. These are the vendors' published prices for the job.

### Do GLiClass and OpenAI Decisions API need an API key?

GLiClass needs no key. OpenAI Decisions API needs an API key.

### Can an agent call GLiClass and OpenAI Decisions API without installing anything?

No hosted endpoint is listed for GLiClass. OpenAI Decisions API has a hosted endpoint at https://api.openai.com/v1/decisions.

### Are GLiClass and OpenAI Decisions API open source?

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


## For agents

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

## Other comparisons with GLiClass or OpenAI Decisions API

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