Topic

Google Cloud Functions & Cloud Run LLM Integration

12 posts on google cloud functions & cloud run llm integration — part of api integration on the n4n AI blog.

Storing provider keys in Google Secret Manager for Cloud Functions

Learn how to store and access google secret manager cloud functions api keys securely, with step-by-step setup and Python code for Cloud Functions.

July 17, 20263 min read

API integrationGuide

Google Cloud Functions gen 2 timeout limits for LLM requests

Practical guide to configuring Cloud Functions Gen2 timeouts for LLM APIs: set limits, stream responses, use async patterns, and avoid provider stalls.

July 17, 20264 min read

API integrationAnalysis

Google Cloud Functions cold starts and LLM API latency

Analyze how Google Cloud Functions cold starts affect LLM API latency, with concrete code, tradeoffs, and a decisive architecture recommendation.

July 17, 20265 min read

API integrationTutorial

Deploying an OpenAI-compatible proxy on Cloud Run

Learn how to build and deploy a cloud run openai-compatible proxy with FastAPI and Docker, forwarding LLM requests to any OpenAI-style backend.

July 17, 20263 min read

API integrationTutorial

Deploying a containerized LLM proxy on Google Cloud Run

Build and deploy a cloud run containerized llm proxy on Google Cloud Run with FastAPI and Docker. Step-by-step tutorial with runnable code. Forward OpenAI-compatible requests to any LLM backend.

July 17, 20263 min read

API integrationGuide

Cloud Run concurrency settings for streaming LLM requests

Practical guide to tuning Cloud Run concurrency for LLM streaming: defaults, capacity formulas, deploy code, and pitfalls to avoid when scaling streaming proxies.

July 17, 20264 min read

API integrationGuide

Cloud Run autoscaling for high-throughput LLM API traffic

Practical guide to Cloud Run autoscaling for LLM traffic: set concurrency, stream, handle provider limits, and load test for high throughput.

July 17, 20264 min read

API integrationHow-to

Streaming LLM responses from Cloud Run with HTTP/2

Learn how to deploy a Cloud Run service that streams LLM responses over HTTP/2, with runnable code and verification steps for engineers.

July 16, 20263 min read

API integrationComparison

Google Cloud Functions vs Cloud Run for LLM API workloads

Head-to-head comparison of Google Cloud Functions vs Cloud Run for LLM API workloads, covering latency, cost, scaling, and which to choose for your use case.

July 16, 20264 min read

API integrationComparison

Cloud Functions vs Cloud Run vs AWS Lambda for LLM APIs

Engineering comparison of cloud functions vs cloud run vs lambda for LLM API hosting: cost, latency, limits, ergonomics, and which to choose per use case.

July 16, 20264 min read

API integrationTutorial

Calling n4n.ai from Google Cloud Functions in Node.js

Step-by-step tutorial to build a serverless Node.js LLM API on Google Cloud Functions that calls an OpenAI-compatible gateway, with deploy and test code.

July 16, 20263 min read

API integrationTutorial

Building a Cloud Run chatbot service with FastAPI and n4n.ai

Hands-on tutorial: deploy a FastAPI chatbot to Google Cloud Run proxying an OpenAI-compatible LLM gateway, with streaming and Docker setup.

July 16, 20263 min read