Topic

C# / .NET LLM API Integration

13 posts on c# / .net llm api integration — part of api integration on the n4n AI blog.

Unit testing LLM API integrations in C# with Moq

Learn how to unit test LLM API integrations in C# using Moq to isolate HTTP calls, mock responses, and verify behavior without hitting live endpoints.

July 17, 20262 min read

API integrationComparison

System.Text.Json vs Newtonsoft.Json for LLM responses

A pragmatic head-to-head comparison of System.Text.Json vs Newtonsoft.Json for parsing, streaming, and serializing LLM responses in C# .NET apps.

July 17, 20264 min read

API integrationHow-to

Streaming LLM responses in .NET with IAsyncEnumerable

Step-by-step guide to dotnet iasyncenumerable streaming llm integration in C#, with runnable code and verification for production-grade apps.

July 17, 20263 min read

API integrationComparison

Semantic Kernel vs raw HTTP for .NET LLM integration

Compare Semantic Kernel vs raw HTTP dotnet for production LLM apps: capabilities, cost, latency, ergonomics, ecosystem, limits, and which to choose.

July 17, 20265 min read

API integrationHow-to

Polly retry policies for OpenAI API calls in .NET

Implement resilient LLM calls in C# using Polly retry policies for OpenAI API failures, with step-by-step code for transient error handling.

July 17, 20263 min read

API integrationHow-to

NuGet setup for an OpenAI-compatible C# client

Install and configure a NuGet OpenAI-compatible C# client for .NET apps: package setup, base URL, auth, and a test chat call to verify.

July 17, 20264 min read

API integrationGuide

IHttpClientFactory best practices for LLM API clients

Practical patterns for using IHttpClientFactory in .NET to build resilient LLM API clients, covering pooling, streaming, retries, and metering.

July 17, 20263 min read

API integrationHow-to

Handling 429 rate limits in .NET LLM clients

Practical steps to handle dotnet 429 rate limit llm errors in C# clients with retry, backoff, and fallback to keep LLM calls resilient.

July 17, 20263 min read

API integrationHow-to

Dependency injection for LLM clients in .NET 8

Learn to implement a dotnet 8 dependency injection llm client using OpenAI-compatible endpoints, resilient provider fallbacks, and testable service layers.

July 17, 20263 min read

API integrationComparison

Azure OpenAI SDK vs OpenAI-compatible REST in .NET

Head-to-head comparison of Azure OpenAI SDK vs OpenAI-compatible REST in .NET: capabilities, cost, latency, ergonomics, ecosystem, limits, and verdict.

July 17, 20264 min read

API integrationGuide

Async/await patterns for concurrent LLM calls in C#

Hands-on guide to c# async await concurrent llm calls: use Task.WhenAll, SemaphoreSlim, and proper cancellation to build resilient .NET LLM integrations.

July 17, 20264 min read

API integrationTutorial

Calling the OpenAI API from C# with HttpClient

Learn how to call the OpenAI API from C# using HttpClient with a hands-on tutorial covering auth, requests, streaming, and error handling.

July 16, 20262 min read

API integrationTutorial

Building a minimal API wrapper for n4n in ASP.NET Core

Hands-on tutorial: build an ASP.NET Core minimal API wrapper for the n4n LLM gateway using its OpenAI-compatible endpoint with C#.

July 16, 20263 min read