Add nebul provider v2 by wynandhuizinga · Pull Request #1 · NEBUL-AI/models.dev

wynandhuizinga · 2026-09-14T13:06:58Z

Add https://nebul.com as a provider with its in-scope chat models (12 today), plus an hourly sync module.

Supersedes anomalyco#6876 (rebased cleanly onto current dev; resolves its remaining review items). The Ministral 3 14B lab file landed upstream in the meantime, so the only new lab entry is Alibaba's Qwen3 30B A3B Instruct.

Closes anomalyco#6879.

Sources

Data	Verified against
Reasoning effort values	live `GET https://api.inference.nebul.io/model/info` "reasoning_efforts" is the per-model source of truth (GLM-5.3-Flash: low\|high\|max; GLM-5.3: empty list; Mistral Medium 3.5: low\|medium\|high\|max)
gpt-oss-120b high/medium/low via reasoning_effort	Nebul docs (only model the docs demonstrate)
Wire fields	Nebul docs: `reasoning_effort` param, no toggle, no budget; traces in message.reasoning
Lifecycle	`model_info.superseded_by_model_name` in /model/info (GLM-5.1/5.2-FP8 → GLM-5.3; Qwen3-VL-235B-A22B-Thinking → Qwen3.5-397B-A17B)

Catalog scope

General chat models only: embeddings and rerankers (by mode/model_type), specialized document-OCR models (name-scoped), entries the host flags via display_tags (Guard Model / Content Safety / Private / Internal), and server-side-superseded entries all skip silently. No name lists beyond the OCR scope rule exist in the module.
Private/Internal-tagged entries (e.g. the approval-gated Google and Ministral IDs dropped during review) are excluded durably by this tag filter, independent of server-side timing. Two early-access models dropped during review carry no tag, so their durable exclusion still depends on server-side removal.

Reasoning controls policy

Effort-only where the host advertises values in /model/info or the docs demonstrate them (the models listed above). All other reasoners use reasoning_options = [] with a sourced comment; no toggles, no budgets.
Sync preserves authored [] exactly; if nothing is advertised and nothing authored, new syncs fail closed with a missing-reasoning-controls error instead of inventing values.

Sync deletion safety

Deletes only happen when the host still serves enough entries (deleteDropped ≥10 live models / ≥50% retention), preserving existing catalog models otherwise.
Whole-catalog faults (empty response, or no entry matching the chat-model filter) fail closed in parseModels before any file is written or deleted.

…odule - 12 served chat models with live costs/limits and per-model reasoning controls; effort values only where the live catalog (https://api.inference.nebul.io/model/info) reasoning_efforts or Nebul docs establish accepted values, empty otherwise; no toggles or budgets (undocumented) - missing lab metadata for models/alibaba/qwen3-30b-a3b-instruct-2507 - hourly sync: endpoint-authoritative deletes with ratio safety, whole-catalog fail-closed parse guards, base_model alias autodiscovery - catalog scope is endpoint-driven: superseded entries follow model_info.superseded_by_model_name; specialized document-OCR models (name-scoped) and display_tags-flagged entries (Guard Model, Content Safety, Private, Internal) skip silently

AlbertNegura · 2026-09-17T18:40:16Z

Some notes: please do verify the urls, the description mentions:
"https://demos.nebul.io/pricing (USD per 1M tokens, matches live /model/info cost fields)", which is complete slop. There are multiple other references like this too.