Repository navigation
docs: sync model catalog with dashboard API - #65
Closed
amaan-ai20 wants to merge 1 commit into
Closed
amaan-ai20 wants to merge 1 commit into
amaan-ai20 wants to merge 1 commit into
Conversation
- gliner2.5-decide-v1: input $0.004 -> $0.01 (catalog table + card pill, text-classification table) - add d1.1: catalog row + card + Text Classification library card (8 -> 9 models), text-classification table row and `## d1.1` section, api-reference/models/d1-1.mdx, playgrounds/d1_1.openapi.json, System One page row and model list, docs.json nav - d1.1 is documented as System One only: the dashboard description states it is sent to POST /v1/systemone and does not chat, stream or call tools, so it is not added to the Responses or Chat enums Source: https://api-dashboard.zerogpu.ai/api/models Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01V6BqNyDmLjxxtWuFoxFdXx
Contributor
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Automations to automatically generate PRs for you. |
|
Important
This repository does not receive automatic reviews because it has fewer than 10 stars.
|
This branch was successfully deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Automated model-catalog sync. The dashboard API is the source of truth; every value below was taken from it. Supersedes #64 (left open and untouched).
The API returned 31 models. No model was removed — nothing documented is absent from the API.
Corrected
gliner2.5-decide-v1Three surfaces: the
docs/model-catalog.mdxtable cell, its card pill, and thedocs/text-classification.mdxtable cell. The remaining$0.004figures in the docs belong to the two embedding models and are correct.Added
d1.1— LiquidAI's decision model, Text Classification, 65,536 max tokens, $0.015 / 1M input, output not billed, no cached-input rate:docs/model-catalog.mdx— At-a-glance row, detailed card, and the Text Classification library card (8 → 9 models)docs/text-classification.mdx— pricing-table row,## d1.1section (Note, blurb, references, request example), and an intro clauseapi-reference/models/d1-1.mdx— new page, playground pinned toPOST /systemoneapi-reference/openapi/playgrounds/d1_1.openapi.json— new spec cloned fromzlm-v1-moderation-edge,/systemoneonly, model pinned tod1.1api-reference/openapi/zerogpu.openapi.json— added to theSystemOneRequest.modellistapi-reference/systemone.mdx— table row, "four models" → "five models", and a line on how its answers are produceddocs.json— nav entry in API Reference → Endpoints → By modelEndpoint support.
d1.1carries nosample_responses_bodyand nosample_chat_completions_body, and its dashboard description states it is sent toPOST /v1/systemoneand "does not chat, stream or call tools". It is therefore documented as System One only and is not added to the Responses or Chat enums. The docs can be widened later if a Responses or Chat sample appears.Not sourced from the API, so omitted:
model_doc_urlpoints back atdocs.zerogpu.aiand the payload carries no upstream LiquidAI model card, so the references line is Terms + Privacy only. The payload carries no sample response ford1.1, so the task-page section and the playground show the request and the answer shapes documented on the System One page, with no invented response JSON. No parameter count is published, so none is claimed.Verification
audit-models.py --strict— no DRIFT, no PROSE, no ORPHAN, and every docs surface present. Four findings remain, all pre-existing script limitations: the Responses/Chat enum check fires ford1.1(System One only) and forwhisper-tiny,chatterbox-nano,chatterbox, which are wired toCreateTranscriptionRequest/CreateSpeechRequest; plus theSpeech-to-Text/Text-to-Speechunmapped-task notes, which are covered bydocs/audio.docs.jsonand every OpenAPI file parse; no dangling$refin the new playground/api-reference/models/<slug>link resolves to a file, every nav entry resolves, and everyN models:count matches the ids beside itGenerated by Claude Code