docs: add Neon AI Gateway provider guide - #362
Open
mezotv wants to merge 3 commits into
Open
Conversation
mezotv
marked this pull request as ready for review
July 25, 2026 11:05
|
Codex usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits. |
`gpt-5-2-codex`, `gpt-5-1-codex-max` and `gpt-5-1-codex-mini` are not in Neon's model catalog. The models served only through the Responses endpoint are `gpt-5-3-codex` and `gpt-5-5-pro`.
…odels The set of models Neon serves only through the Responses API changes as models are added and retired, so a list written into this page goes stale without anyone noticing. Point at the Endpoints column in Neon's model catalog, which is the published source for it, and keep the current models as an example rather than as the definition.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a provider page for Neon AI Gateway under Providers > Custom Providers, alongside the existing Exa, xAI, OpenRouter, and Concentrate pages.
What this is
Neon AI Gateway serves an OpenAI-compatible chat completions endpoint. The page documents it through PromptLayer's existing Custom Providers mechanism: create a custom provider with Client: OpenAI and a base URL, the same way the OpenRouter page does it. There is no new PromptLayer code, no SDK change, and nothing here claims native Neon support.
Why it needs its own page
Two things work differently from the custom providers already documented:
mainis valid onmainand on every branch forked from it, so one key usually covers preview and CI branches.The page also flags that the Codex model variants are served only on the Responses API path and return a
400against a/v1base URL. Someone picking model IDs off the Neon catalog would otherwise run into that.Changes
features/neon-integration.mdx(new)docs.json: one nav entry in the Custom Providers groupThe diff is insertion only, 115 added lines and 0 removed. No existing page was edited.
Sources
Each claim was checked against Neon's documentation:
aws-us-east-2, and the list of upstream providersai_gateway:invokescope and branch lineage rules/v1base URLpricing: nullonGET /v1/modelsChecks
Run locally and passing:
jq empty docs.jsonandjq empty openapi.json/features/custom-providers,/features/supported-providers, and/sdks/python#using-the-run-method-recommended<Info>and<Warning>tags balance, the nav slug matches the file path, and the entry appears exactly onceNot run:
mint broken-linksandmint validate. The npm registry proxy on the machine I worked from returns403 Forbiddenfor themintpackage, and I did not route around it. Both commands run in CI on this PR, so please treat the CI result as authoritative over my local checks.Against the AGENTS.md review checklist
*-integrationsibling pages, including their Title Case headings and their provider and model configuration layoutopenapifrontmatter: not applicable, this is not an endpoint page