docs: add Dynoyard endpoint guide - #731
Open
jeremyrx7 wants to merge 2 commits into
Open
Conversation
|
@jeremyrx7 is attempting to deploy a commit to the LibreChat's projects Team on Vercel. A member of the Team first needs to authorize it. |
jeremyrx7
force-pushed
the
docs/dynoyard-endpoint
branch
from
August 16, 2026 10:10
1a9c5c0 to
9065f38
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds a Dynoyard custom endpoint guide under the LibreChat YAML AI endpoints docs. Dynoyard is an OpenAI-compatible gateway for open-weight models, with routing and failover across the providers that serve them.
The example uses:
DYNOYARD_KEYhttps://<your-org>.dynoyard.app/v1— each account has its own subdomain, so the reader substitutes their workspace slug, similar to the Azure pagekimi-k3as the default model andqwen-plus-3-7fortitleModelmodels.fetch: trueso LibreChat can load the live model list from/v1/models, which the gateway serves in the OpenRouter response shapeAlso adds the provider icon and the
meta.jsonsidebar entry. Locale files are left alone sotranslate_docs.ymlcan generate them.Testing
pnpm typecheckpnpm exec prettier --checkon the five changed filespnpm exec eslint --max-warnings 0on the three TS filespnpm build— compiled successfully, 2891 static pages generated, anddynoyard.htmlrenders with the icon SVG inlinecurl -s https://jeremy.dynoyard.app/v1/models | jq -e '.data | map(.id) | contains(["kimi-k3","glm-5-2","qwen-max-3-7","minimax-m3"])'— confirms every model ID named in the page is really served