--- title: LLMs belong in your backend | daily.dev description: Neon announces AI Gateway, a new component of its serverless Postgres backend that routes LLM calls (both frontier and open-weight models) through a single... canonical: https://daily.dev/posts/llms-belong-in-your-backend-z3fdep2tj twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: LLMs belong in your backend | daily.dev og:description: Neon announces AI Gateway, a new component of its serverless Postgres backend that routes LLM calls (both frontier and open-weight models) through a single... og:url: https://daily.dev/posts/llms-belong-in-your-backend-z3fdep2tj og:image: https://api.daily.dev/og/posts/z3fdEP2Tj.png og:image:alt: LLMs belong in your backend og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # LLMs belong in your backend **[Neon](https://daily.dev/sources/neontech)** · 8 min read · 1 upvotes · 0 comments ## Summary Neon announces AI Gateway, a new component of its serverless Postgres backend that routes LLM calls (both frontier and open-weight models) through a single Neon credential instead of separate API keys per lab. Hosted on Databricks' Foundation Model APIs infrastructure, it unifies billing on the Neon invoice with no markup over published lab pricing, supports OpenAI-compatible and native provider routes, and inherits Neon's branching model so each database branch gets its own gateway host and credentials. The gateway is currently in beta and free to use, with observability and spend controls planned as follow-ups. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is Neon AI Gateway and how does it let me call different LLMs without managing separate API keys? Neon AI Gateway is a unified endpoint inside the Neon backend that routes calls to frontier and open-weight models hosted on Databricks Foundation Model APIs. Instead of separate keys for OpenAI, Google, or Anthropic, you use one Neon bearer credential with the ai_gateway:invoke scope, point your existing SDK at a new base URL, and switching models becomes changing a string on an OpenAI-compatible /v1 path. _Developers comparing LLM providers can follow how backends like Neon's AI Gateway simplify multi-model access on daily.dev._ ### Does switching to Neon AI Gateway add extra markup on top of OpenAI or Anthropic API pricing? No, Neon AI Gateway passes through each provider's published per-token rates without markup, and usage appears consolidated on the Neon invoice instead of separate lab statements. This lets teams see token spend alongside the rest of their backend costs while still paying standard published pricing for both open-weight and proprietary models. _Anyone budgeting LLM spend across multiple providers can track billing-model changes like this one on daily.dev._ ### How does branching work with LLM API credentials in Neon's AI Gateway? Each Neon branch gets its own AI Gateway host, so a preview deploy hits a distinct endpoint rather than production's. Credentials follow lineage: one created on main works on main and its descendants but not on sibling branches, so PR bots and feature branches each use scoped credentials tied to their own gateway host, which is deleted when the branch is deleted. _Teams designing branch-based preview environments can watch for infrastructure changes like this on daily.dev._ ## Similar posts on daily.dev - [LiteLLM: AI Gateway for LLMs — Features Overview](https://daily.dev/posts/litellm-ai-gateway-for-llms-features-overview-93hxfkgaq) · ITNEXT · 0 upvotes · 0 comments - [We're building the boring backend for apps and agents](https://daily.dev/posts/we-re-building-the-boring-backend-for-apps-and-agents-ovc7nb5ck) · Neon · 5 upvotes · 0 comments - [Build intelligent agents with every leading model on Databricks](https://daily.dev/posts/build-intelligent-agents-with-every-leading-model-on-databricks-qsvt8dbec) · databricks · 1 upvotes · 0 comments - [Open-weight models are fast on Neon AI Gateway. Here's why](https://daily.dev/posts/open-weight-models-are-fast-on-neon-ai-gateway-here-s-why-dtkhuv4up) · Neon · 0 upvotes · 0 comments - [Untitled](https://daily.dev/posts/untitled-m9iztiroa) · SitePoint · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#postgresql](https://daily.dev/tags/postgresql), [#databricks](https://daily.dev/tags/databricks), [#ai-gateway](https://daily.dev/tags/ai-gateway) [View this post on daily.dev](https://daily.dev/posts/llms-belong-in-your-backend-z3fdep2tj) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"LLMs belong in your backend","url":"https://daily.dev/posts/llms-belong-in-your-backend-z3fdep2tj","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/llms-belong-in-your-backend-z3fdep2tj"},"datePublished":"2026-08-17T13:15:54.476Z","dateModified":"2026-09-14T09:32:55.864Z","description":"Neon announces AI Gateway, a new component of its serverless Postgres backend that routes LLM calls (both frontier and open-weight models) through a single...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/e92b298396299803487ddc133b0f7b61?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/e92b298396299803487ddc133b0f7b61?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Neon","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Neon","logo":"https://media.daily.dev/image/upload/s--65EDghou--/f_auto/v1724339118/logos/neontech","url":"https://daily.dev/sources/neontech"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/llms-belong-in-your-backend-z3fdep2tj","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,postgresql,databricks,ai-gateway","timeRequired":"PT8M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Neon","item":"https://daily.dev/sources/neontech"},{"@type":"ListItem","position":3,"name":"LLMs belong in your backend"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/llms-belong-in-your-backend-z3fdep2tj#faq","mainEntity":[{"@type":"Question","name":"What is Neon AI Gateway and how does it let me call different LLMs without managing separate API keys?","acceptedAnswer":{"@type":"Answer","text":"Neon AI Gateway is a unified endpoint inside the Neon backend that routes calls to frontier and open-weight models hosted on Databricks Foundation Model APIs. Instead of separate keys for OpenAI, Google, or Anthropic, you use one Neon bearer credential with the ai_gateway:invoke scope, point your existing SDK at a new base URL, and switching models becomes changing a string on an OpenAI-compatible /v1 path. Developers comparing LLM providers can follow how backends like Neon's AI Gateway simplify multi-model access on daily.dev."}},{"@type":"Question","name":"Does switching to Neon AI Gateway add extra markup on top of OpenAI or Anthropic API pricing?","acceptedAnswer":{"@type":"Answer","text":"No, Neon AI Gateway passes through each provider's published per-token rates without markup, and usage appears consolidated on the Neon invoice instead of separate lab statements. This lets teams see token spend alongside the rest of their backend costs while still paying standard published pricing for both open-weight and proprietary models. Anyone budgeting LLM spend across multiple providers can track billing-model changes like this one on daily.dev."}},{"@type":"Question","name":"How does branching work with LLM API credentials in Neon's AI Gateway?","acceptedAnswer":{"@type":"Answer","text":"Each Neon branch gets its own AI Gateway host, so a preview deploy hits a distinct endpoint rather than production's. Credentials follow lineage: one created on main works on main and its descendants but not on sibling branches, so PR bots and feature branches each use scoped credentials tied to their own gateway host, which is deleted when the branch is deleted. Teams designing branch-based preview environments can watch for infrastructure changes like this on daily.dev."}}]} ```