Gemini Decision 1 vs GLiClass

Gemini Decision 1 80

Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. No published machine-readable contract for the Decisions endpoint; the request and response types are generated and typed in google-genai 3.2.0, Apache-2.0 (10 of 25). llms.txt with Markdown twins on the platform (10). The guide and model page say what the endpoint is for and list what it doesn't do (no caching, Batch, Flex, Priority, function calling, structured outputs or text generation; no YouTube or gs:// sources; history only as text) (18 of 20). Fields carry stated rules: question keys match [A-Za-z0-9_-]+ up to 64 characters, 1 to 1,000 questions, 2 to 255 options or levels, option keys 1 to 128 characters, P(true) between 0.01 and 0.99, nesting to 100 levels (14 of 15). Python, JavaScript and REST examples, and errors documented as HTTP 400 with codes safety, prohibited_content, blocklist, image_safety and content_blocked (13 of 15). Dated SDK changelog and the platform's dated changelog (15). 10 + 10 + 18 + 14 + 13 + 15 = 80.

GLiClass 49

Read for a model the owner serves. No OpenAPI file. The serving page documents the seven request fields of POST /gliclass and the response array in a table, and the pipeline's Python signatures carry type hints (10 of 25). docs.knowledgator.com has no llms.txt (404). The README, docs/streaming.md and the model cards are Markdown (5 of 10). The cards and docs name the intended uses (topic, sentiment, intent, natural language inference, reranking) and print per-dataset F1 that shows the weak cases, such as 0.3376 on sst5 for base v3.0. The base card has no limitations section and says nothing on calibration (11 of 20). Labels are free strings or a dict of groups, the mode is one of two values and threshold is a number. The HTTP handler reads fields from the body without validation, and a list in texts is cut to its first item (8 of 15). Examples for every mode in the docs. The handler's 400 and 404 answers are not documented, and a request without labels gets a 404 (8 of 15). Versions on PyPI and version numbers in model names, with three one-line GitHub release notes and no changelog (7 of 15). Version 0.1.22 adds a second HTTP interface under /v1/ (process, batch, models, capabilities, health) with coded errors carrying an HTTP status and a JSON path, in the code only; neither the docs site's serving page nor the README describes it on 4 November, so no line moves.

Gemini Decision 1 60

Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. No machine payment protocol (0). The pricing page lists $0.10 per million input tokens on the paid tier for every modality and no output charge, without a login (20). Free of charge on the free tier (20). A Google account and an AI Studio key come first (0). 0 + 20 + 20 + 0 = 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

GLiClass 90

Free Apache-2.0 software with nothing to buy, so 20 + 20 + 20 for pricing, free use and no sign-up under the self-hosted rule. No payment protocol (0). Knowledgator's hosted platform and its plans were unreachable from our network on 8 October 2026 and are not graded here. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.

Gemini Decision 1 85

Read on the tool lines, as the other decision-model listings are. Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Answers are probabilities only, and the shared input is billed once across up to 1,000 questions (25 of 25). Limits are written down: 262,144 tokens shared by the input and all questions, 1,000 questions, 2 to 255 options, inline data to 100 MB (50 MB for PDFs), 15 MB per external URL (20 of 20). Errors return HTTP 400 with a named code an agent can branch on, plus the platform's backoff advice (15 of 20). SDK retries and backoff guidance, no idempotency key; nothing is written, so a repeat only costs input again (10 of 20). Three required fields, SDK 3.2 or later in Python and JavaScript, and REST (15 of 15). 25 + 20 + 15 + 10 + 15 = 85.

GLiClass 60

Read as an API an agent calls for a decision, as with the other decision models. The answer is a short list of labels and scores and no text is generated. Text and labels share one sequence, 1,024 tokens by default, with 25 labels by default (17 of 25). The caller sets a threshold, picks single-label or multi-label, and can ask for hierarchical output. The pipeline takes a batch of texts and a chunking pipeline handles long documents. The HTTP endpoint takes one text a request (15 of 20). Errors are {"error": "..."} with 400 or 404 and are undocumented. Truncation of long input is silent (7 of 20). Classification calls are stateless and safe to retry. The server has a request timeout and a queue capacity in its configuration. We found no Retry-After or retry guidance in the serve package or the docs (12 of 20). Loading takes a model, a tokeniser and a pipeline call, and a Python client ships with the server. Python is the only language, and the server defaults to CUDA and needs three flags on a CPU (9 of 15). The 0.1.22 /v1/process errors are actionable in the code (codes such as INPUT_TOO_LONG with a JSON path) but undocumented, so the error line holds.

Gemini Decision 1 79

Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Released on 11 November 2026, the day of this check (30). Deprecations with earliest dates and no stated minimum notice (4 of 12). Shutdowns in the last 90 days kept to their table (4 of 8). Dated changelogs: google-genai 3.2.0's entry adds the Decisions API; the platform changelog wasn't re-read today (11 of 15). SDK replies not sampled (5 of 10). google-genai 3.2.0 tagged the same day with client.decisions.create; the JavaScript SDK is per Google's post (15). Runtimes stated on the platform (10). 30 + 4 + 4 + 11 + 5 + 15 + 10 = 79. The model is hours old, so these lines are the platform's habits more than this model's record.

GLiClass 64

Read as a model, for deprecation notice and model churn rather than release counts, on the lines used for Kev, Vela 2.0, Decider and the other decision models listed as models. The repository tagged v0.1.22 on 31 October 2026 (FP8 serving and a new process API), after v0.1.21 on 16 October (calibration and multimodal training), and the v4 checkpoints were last changed on 24 October (30). No deprecation policy or notice period. Each generation lives in its own Hub repository (v1.0, v2.0, v3.0, Instruct, Multilang, v4) and none has been removed or replaced in place; the v3.0 repositories last changed on 12 August 2025 (5 of 12, level with Decider's and Kev's 5). Four v4 models (edge, 2B, 9B and 27B) arrived from 13 to 24 October 2026 as new repositories, with the earlier ones untouched (5 of 8). 34 commits from v0.1.20 to v0.1.22 under six author names, six of them merges of pull requests (#48 to #53). Issue reply times weren't checked, and the open-issue count is per the 8 October check, not re-read on 4 November. A Discord server is linked (10 of 25). The Python package is current and runs on transformers 5. No other SDK (10 of 15). CI and a uv.lock exist, and PyPI publishing is automated on tags, but the Tests workflow was failing on main, per the 8 October check, not re-read on 4 November (4 of 10). 30+5+5+10+10+4 = 64.

Gemini Decision 1 45

Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Keys bound to a service account and restricted to the Gemini API, with no scopes and a token accepted in the URL (15 of 30, the platform's deduction). The pricing page, read on 11 November, says free-tier content is used to improve Google's products and paid-tier content isn't (10 of 20, the platform's reading). Abuse retention with no number (5 of 15). Request logs for billed projects are described for Generate Content; the Decisions guide says nothing on logging (10 of 15). security.txt and a reward programme, no certification naming the API (5 of 20). 15 + 10 + 5 + 10 + 5 = 45.

GLiClass 38

Read as a model, for retention, training and zero-retention options in place of read-only modes, on the lines used for Kev, Vela 2.0 and the other decision models listed as models. No account. The Ray Serve deployment checks no credential and has no option for one in 0.1.22, and the command line still binds to 0.0.0.0 by default (6 of 30). Self-hosted, so nothing reaches Knowledgator and no caller data can train a model, and the package has no telemetry code, but no project page says so, where Kev's cards and Vela 2.0's runtime reference state it for their 18 (15 of 20, level with Strands Decider and Granite Switch). The output is labels and scores, so no untrusted text comes back. The docs warn that the safety checkpoints can miss new or obfuscated attacks. Nothing documents how hostile text moves a score (10 of 15). The server logs start-up and label truncation and keeps request statistics, and the docs describe no per-call record (3 of 15). No SECURITY.md, no security.txt on knowledgator.com (404 per the 8 October check, not re-read on 4 November) and no bounty. Weights are safetensors, though the v4 2B repository also holds a pickled training_args.bin beside them. PyPI releases use trusted publishing. gliclass/config.py still loads an unknown encoder's configuration with trust_remote_code=True (4 of 20). 6+15+10+3+4 = 38.

Gemini Decision 1 70

Model reading for gemini-decision-1 on the Gemini API's Decisions endpoint. Platform facts are the Gemini API listing's (gemini-api, re-read 1 November), carried over as RULES.md allows for a model on an already graded platform. Closed service with clear terms, SDKs Apache-2.0 (15). The pricing page states that free-tier content is used to improve products and paid-tier content isn't; abuse retention has no number (15 of 30). Deprecations table; the model page names no deprecation for this model (15 of 20). Data may be cached anywhere Google has facilities; no subprocessor list checked (5 of 20). Every benchmark, latency and cost comparison is Google's own, and the post gives charts without scores in its text. 15 + 15 + 15 + 5 = 50.

GLiClass 65

Apache-2.0 for the library and the weights, with train.py, the training datasets named on the card and an arXiv paper (30). Self-hosted, so inputs stay on the owner's hardware, though no project page says so. The company's terms of use and privacy policy of 21 September 2023 (terms re-read on 4 November) covers its website and services, not the library (18 of 30). No deprecation policy. Older model generations stay on the Hub without a notice of which are current (2 of 20). We found no telemetry code in the package and no statement either way. Weights download from the Hugging Face Hub (10 of 20).