Skip to content

docs: add Neon AI Gateway provider guide - #362

Open
mezotv wants to merge 1 commit into
MagnivOrg:masterfrom
mezotv:docs/neon-ai-gateway-provider
Open

docs: add Neon AI Gateway provider guide#362
mezotv wants to merge 1 commit into
MagnivOrg:masterfrom
mezotv:docs/neon-ai-gateway-provider

Conversation

@mezotv

@mezotv mezotv commented Jul 25, 2026

Copy link
Copy Markdown

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:

  • Neon has no single hostname. Each database branch gets its own gateway host, so the base URL points at one branch, and running prompts against several branches means one custom provider per branch.
  • Credentials are branch scoped. A credential created on main is valid on main and 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 400 against a /v1 base 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 group

The diff is insertion only, 115 added lines and 0 removed. No existing page was edited.

Sources

Each claim was checked against Neon's documentation:

  • Overview for beta status, the paid plan requirement, aws-us-east-2, and the list of upstream providers
  • Quickstart for the branch host format and where the Console shows it
  • Authentication for the ai_gateway:invoke scope and branch lineage rules
  • Chat completions for OpenAI compatibility and the /v1 base URL
  • Models for the model IDs, the Responses-only Codex variants, and pricing: null on GET /v1/models

Checks

Run locally and passing:

  • jq empty docs.json and jq empty openapi.json
  • Every internal link and anchor in the new page resolves: /features/custom-providers, /features/supported-providers, and /sdks/python#using-the-run-method-recommended
  • Every external link returns 200
  • <Info> and <Warning> tags balance, the nav slug matches the file path, and the entry appears exactly once

Not run:

  • mint broken-links and mint validate. The npm registry proxy on the machine I worked from returns 403 Forbidden for the mint package, 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

  • Nav section: Providers > Custom Providers, matching where the other provider setup pages live
  • URLs: new page only, nothing moved, no redirects needed
  • Titles, labels, and slugs: follows the *-integration sibling pages, including their Title Case headings and their provider and model configuration layout
  • REST API page format and openapi frontmatter: not applicable, this is not an endpoint page
  • Copy: task oriented, no marketing language, no internal implementation detail

@mezotv
mezotv marked this pull request as ready for review July 25, 2026 11:05
@chatgpt-codex-connector

Copy link
Copy Markdown

Codex usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits.
Credits must be used to enable repository wide code reviews.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant