Repository navigation
docs: sync model catalog with dashboard API - #68
Merged
Merged
Conversation
- zlm-v1-tool-decisions: input $0.05 -> $0.04, output $0.15 -> Not billed (catalog table + card pills, text-generation, open-weight) - zlm-v1-tool-decisions: quantization bf16 -> Q8_0 (text-generation, model page) - add gpt-oss-20b: catalog row + card, Text Generation table row and section, open-weight row + card, model page, playground spec, Chat Completions enum, docs.json nav, Open Weight 10 -> 11 and Text Generation 16 -> 17 counts Source: https://api-dashboard.zerogpu.ai/api/models Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01V6BqP15LdFrfZiE9gS5WSm
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Corrected
zlm-v1-tool-decisionszlm-v1-tool-decisionsNot billed(API reports0)zlm-v1-tool-decisionsFixed in
docs/model-catalog.mdx(table + card pills),docs/text-generation.mdx,docs/open-weight.mdx, andapi-reference/models/zlm-v1-tool-decisions.mdx. The output pill was dropped rather than written as$0.00, matching the other zero-output models (d1.1,gliner2.5-decide-v1), whose cards carry an input pill only.Added
gpt-oss-20b— Summarization, 131,072 max tokens, $0.02 in / $0.10 out / $0.01 cached per 1M, 21B params (3.6B active), MXFP4.docs/model-catalog.mdx: At-a-glance row (afterqwen3-30b-a3b-fp8, by descendingdisplayPriority), detailed card, and the Open Weight (10 → 11) and Text Generation (16 → 17) library countsdocs/text-generation.mdx: pricing row +## gpt-oss-20bsection, intro updateddocs/open-weight.mdx: pricing row + card, intro "ten" → "eleven" (itsterms_urlis the upstream gpt-oss licence)api-reference/models/gpt-oss-20b.mdxandapi-reference/openapi/playgrounds/gpt-oss-20b.openapi.json(new)api-reference/openapi/zerogpu.openapi.json: added toCreateChatCompletionRequestenumdocs.json: nav entry under API Reference → By modelNotes on this addition:
sample_responses_bodyforgpt-oss-20b, so per the skill it is documented as Chat Completions only — Chat enum only, chat-only<Note>on its section, playground pinned toPOST /chat/completions. This can be widened once a Responses sample or an explicit confirmation exists.llama-3.2-3b-instruct-fastsection.pricing.descriptiononly. Not stated by the API and therefore omitted: benchmarks, latency, language counts, and tool/streaming support.integrations/hermes.mdx,integrations/vercel-ai-sdk.mdx,integrations/litellm.mdx) carry curated model subsets and per-SDK capability matrices, sogpt-oss-20bwas not added to them.Removed
Nothing — the API still returns every documented model.
Verification
audit-models.py --strict— clean apart from three NOTE lines for the unmappedSpeech-to-Text/Text-to-Speechtasks, which are already documented ondocs/audio.mdxdocs.jsonand all 36 OpenAPI files parse/api-reference/models/<slug>link resolves to a file; all 117 nav pages exist; everyN models:count matches the ids beside itGenerated by Claude Code