Tutorials

Guides, walkthroughs, and integration how-tos.

Reranking in RAG: How to Fix Bad Retrieval with a Reranker

When a RAG (Retrieval-Augmented Generation) app gives wrong answers even though the right information is in your documents, retrieval is often the cause. Vector search is great at finding chunks on the right topic, but it often falls for near misses, like pulling the bucket limit for the Enterprise plan when the user asked about the Growth plan. Reranking in RAG fixes this by taking your vector search’s top 30 candidates and passing them through a dedicated cross-encoder model that re-scores each chunk directly against the question.

November 13, 2026

How to Stop an AI Agent Stuck in an Infinite Loop

An AI agent gets stuck in an infinite loop when a model keeps calling a tool that fails, usually with the same arguments, because nothing in the agent loop tells it to stop. Each retry resends the whole conversation, so every turn costs more than the last, and a loop left running overnight can cost thousands of dollars.

November 12, 2026

How to Benchmark LLMs

Choose models using evidence from your application’s inputs and output formats. Run identical tasks through OpenRouter and compare graded accuracy, billed cost, and request time. On our 60 synthetic tasks, GPT-6.1 Sol passed 180/180 trials across three repeats under the tested contracts and settings.

November 12, 2026

LLM API Rate Limits: How to Fix OpenAI and Claude 429 Errors

A 429 Too Many Requests error means you sent more requests or tokens than your limit allows in the current time window. OpenAI, Anthropic and OpenRouter all return it, and it usually shows up the first time an app runs under real load or a batch job fans out across several workers.

November 11, 2026

How to Build a Voice AI Agent

A voice agent needs to do more than generate a good answer. It must understand what someone said, decide what to do, call any needed tools, and start speaking again before the pause gets awkward.

November 10, 2026

How to Get Structured Output from Any LLM: JSON Schema, Tool Calls, or a Decision Model

When your code reads fields from a model's reply, like an order ID or a refund amount, it expects clean JSON every time. Most of the time, it gets it. But now and then the model wraps the JSON in a code fence, adds a field you didn't ask for, or sends a number as text, and your code breaks. If you use several models, one fix won't cover them all, because each model and provider handles structured output in its own way.

November 10, 2026

Build an AI Code Reviewer with OpenRouter

Code reviewers that only read a Git diff have to guess whether a change breaks anything, and their fixes come back as prose you apply by hand. This guide builds a Python reviewer on the OpenRouter Responses API that uploads your changed files into a Linux sandbox, runs checks to confirm each bug, and returns validated patches. A review takes one to four minutes and costs $0.015 to $0.045.

November 1, 2026

How to Build Your Own Always-On AI Agent

An always-on AI agent wakes up on a schedule, checks something with tools, and reports or acts without you asking. This tutorial builds one in TypeScript with the OpenRouter Agent SDK that watches Hacker News, remembers what it has seen across restarts, stops any run at five cents, and waits for your approval before it posts.

October 31, 2026

How to Extract Tables from a PDF with an LLM

Send a PDF to a model that reads files, with a strict JSON schema for one row, and you get typed rows back, even from scans and tables that run across pages. We tested five routes on five PDFs and found two failures that return a normal response with no error, and the checks that catch them.

October 29, 2026

How to Prevent Prompt Injection: 13 Attacks, Tested

If your app has a model read documents, emails or web pages, anyone who writes in them can try to give it instructions. We ran 25 attacks against four current models with each defense on and off. Labels cut attack emails, but only checking every tool call with Armor stopped all of them.

October 29, 2026

Claude 529 Overloaded: What It Means and How to Fix It

A 529 overloaded_error from Claude means Anthropic's API is out of capacity for the model you asked for, not that your key or plan is wrong. This guide shows how to retry with backoff, send the same Claude model to another provider through OpenRouter, add a fallback model, and stop the error in Claude Code.

October 28, 2026

Hit Your Claude Code Usage Limit? How to Keep Coding

When Claude Code hits your plan's five-hour or weekly limit, you can keep working by pointing it at an OpenRouter API key. You pay per token for the same Claude models, with no usage window. This guide sets it up as a separate command, checks the cost, and switches back when your plan resets.

October 28, 2026

Model Routing for Support Bots: Cheap-First FAQ Handling

Cheap-first routing sends routine support questions to a small, inexpensive model and escalates selected hard or uncertain requests to a stronger one. This guide compares the three application-side routing patterns, separates what your application owns from what OpenRouter's Auto Router and model fallbacks handle, walks through a support flow with a copyable request, and sets out how to measure escalation rate and cost per resolved ticket.

October 2, 2026

How to Gate Pull Requests on LLM Evals in CI

A one-line prompt change can ship an agent that tells customers the wrong refund window, and nothing in a normal CI pipeline checks what the model says. This guide builds a fixed eval set for a support agent, a script that exits non-zero below a measured threshold, and a GitHub Actions job that blocks the merge when the pass rate drops.

October 1, 2026

AI Agent Regression Testing After a Prompt or Model Change

An agent's behavior can change when you edit a prompt, swap a model, change a tool schema, or change what retrieval returns. This guide covers the locked case set, the per-case behavioral contract, and how to run the same suite against two concrete model slugs through OpenRouter so the diff shows what the change did.

September 30, 2026

Building a Golden Eval Dataset from Production Traffic

A golden eval dataset is a curated set of production inputs with reviewed expected outputs, versioned in Git and run before every deploy. This guide covers the five steps to build one from live traffic and how to run the same set against many candidate models through one API.

September 30, 2026

How to Test Tool-Calling Accuracy in AI Agents

An agent can call the wrong tool, or call the right tool with the wrong arguments. This guide covers three ways to test each failure mode, a Python harness that grades both, and how to run the same test cases against several tool-capable models through OpenRouter.

September 30, 2026

How to Use Jev: Moderation with the Jev API in TypeScript

A method for putting Jev to work on a new problem, worked end to end on marketplace listing moderation: what stays in code, what Jev sees, how to phrase the questions, and how to turn its probabilities into publish, hold, or reject.

September 23, 2026

Jev vs LLM-as-a-Judge

An LLM judge writes a verdict. Jev returns a probability. We graded the same labeled answers and expert-rated summaries with both, and the difference decides which one you should use for a given rubric. Jev matched the LLM judge on agreement at a fifth of the cost and a tenth of the latency, and its probabilities meant what they said. The LLM judge won on the open rubric.

September 21, 2026

Jev vs LLM: When to Use a Decision Model Instead of Generating Text

Jev returns typed judgments with probabilities. An LLM returns prose. We benchmarked both on 100 support cases through OpenRouter, then wired them together so Jev routes and the LLM writes.

September 19, 2026

Build a Reliable Tool-Calling Agent Loop on OpenRouter

A tool-calling agent loop sends the conversation and tool definitions to a model, runs the tool calls the model returns, appends the results, and repeats until the model answers or a stop condition fires. This guide builds that loop in TypeScript with the OpenRouter SDK, then adds an iteration cap, repeated-call detection, model fallback, and history controls.

September 17, 2026

LLM-as-a-Judge: Score AI Agent Outputs Automatically

An LLM judge is a second model that scores an agent's output against criteria you write in plain language. This guide explains where a judge fits beside deterministic tests and human review, then shows how to add one to an Ori Eval test, compare candidate models, calibrate the threshold against human-labeled examples, and keep evaluation cost under control.

September 14, 2026

OpenRouter Text-to-Speech: API Tutorial in 5 Minutes

Our OpenAI-compatible speech endpoint puts TTS models from Mistral, xAI, Microsoft, and more behind one request shape. Here's the path from API key to a playable MP3 in cURL, Python, JavaScript, and the OpenAI SDK, plus the response checks that keep JSON errors out of your audio files.

September 11, 2026

How to Use OpenRouter Presets: Config-as-Code Guide

A preset is config-as-code for your LLM calls: a named, versioned set of models, system prompts, provider routing, and sampling parameters. Define it once, reference it as @preset/your-slug everywhere, and update every app from the dashboard without a redeploy.

September 10, 2026

Nano Banana API: Edit Images with Gemini in Code

Send a source image and an edit prompt in one request, get the edited image back, and change the editing model by editing a single field. Runnable Python and TypeScript included.

September 9, 2026

How to Choose the Best AI Model (Live, in Your Editor)

There's no single best AI model, only the best model for a given task, budget, and moment. This article describes a six-step framework for choosing one, and how to run every step from your editor through the OpenRouter MCP server.

August 25, 2026

OpenRouter Video Generation API: A Code-First Guide

Every video provider has its own endpoint, job statuses, polling logic, and output format. Our async video API puts Seedance, Veo, Wan, and more behind one submit, poll, and download loop. Here's the full lifecycle in Python and TypeScript.

August 25, 2026

OpenRouter Image Generation: A Code-First API Tutorial

Supporting more than one image provider means handling different endpoints, data formats, and billing models. Our dedicated Image API gives you one request format and one key across supported models. Here's the full prompt-to-local-file workflow in Python and JavaScript.

August 17, 2026

How to Send an Image to an LLM via API (Vision Guide)

To get a model to read a screenshot, you need the right request body. This guide shows the content-array pattern that works across every vision-capable model we support, when to use base64 instead of a hosted URL, and how to build multimodal RAG on top of it.

August 14, 2026

Tool Calling Across Any Model: Write the Loop Once, Swap the Model String

Most tool-calling tutorials cover one provider, so you rewrite the loop when you switch. This guide shows the full loop in Python, JavaScript, and cURL, then runs it against three providers by changing one string.

August 12, 2026

Set Up Team AI Spend Controls on OpenRouter

OpenRouter has five controls for team spend: an organization with a shared credit pool, presets that scope models per workload, per-key spend caps, guardrails that enforce per-member budgets, and the Activity dashboard that shows who spent what. This guide sets them all up in one pass, in order.

August 7, 2026

Using OpenRouter With LangChain: ChatOpenRouter Setup Guide

The LangChain integration now has a dedicated package: langchain-openrouter on PyPI and @langchain/openrouter on npm. Most guides still teach the old ChatOpenAI base_url override. This is the current path, plus the routing economics the docs skip.

July 29, 2026

Image Generation Models: Choosing One, Fixing Errors

The image catalog covers ten labs and the slugs change monthly. Here's how to narrow it down by job, parameter support, and price, plus what each Image API error message means and how to fix it.

July 27, 2026

Transcription on OpenRouter

Send base64 audio to POST /api/v1/audio/transcriptions and get JSON text plus a usage object back, with the same API key you already use for chat. Here's the full request contract, the model families, and the limits to design around.

July 22, 2026

The Cheapest Token Is a Cached One: Prompt Caching + Sticky Routing

Your agent sends the same system prompt, tool definitions, and schemas on every turn. Cache reads cost 0.1x to 0.5x of fresh input, but only if the next request lands on the provider holding the warm cache. Here's how caching and sticky routing work together, and how to confirm they're working.

July 21, 2026

Connect OpenClaw to OpenRouter

OpenClaw has built-in OpenRouter support. One command gives your agents one key, one bill, and automatic failover across hundreds of models. Here's the setup and the fixes for the errors that trip people up.

June 18, 2026

How to Connect SillyTavern to OpenRouter (2026 Guide)

One OpenRouter key gives SillyTavern hundreds of models in a single dropdown, many of them free to start. Here's the five-step connection, the roleplay models to try, and fixes for the errors users hit most.

June 18, 2026

Kilo Code + OpenRouter: Setup, Model Routing, and Free Models

Kilo Code is a bring-your-own-provider coding agent, so adding OpenRouter gives it one key for hundreds of models, provider routing, and failover. Here's the three-step setup plus the kilo.json fields that control routing.

June 17, 2026

How to Use OpenAI Codex CLI with OpenRouter

Codex CLI supports custom OpenAI-compatible providers, so a small config.toml block routes it through OpenRouter. You get provider failover, usage tracking, and one key across every model, with no change to Codex itself.

June 17, 2026

How to Use Claude Code with OpenRouter

Route Claude Code through OpenRouter with three environment variables and no local proxy. You get provider failover, budget controls, and usage visibility on top of the same Anthropic models.

June 16, 2026

How to Use OpenRouter With Any Coding Agent or AI Tool

Any tool that speaks the OpenAI API works with OpenRouter after two changes, the base URL and the key. Here's the setup pattern and the tools that already support it.

June 16, 2026

Free LLM APIs Compared: Rate Limits, Models, and Real Costs (2026)

Stop guessing which free LLM API survives past a side project. Here's how OpenRouter, Groq, Gemini, and 10 more compare on limits, cost, and data use.

June 15, 2026

Keep Your Agent Running When Models Disappear

Anthropic restricted Claude Fable 5 just days after launch. If your code hard-codes a model slug, that becomes your outage too. Presets move model choice to the server so you can swap models, set fallbacks, and enforce a data policy without redeploying.

June 15, 2026

How to Use Hermes Agent with OpenRouter: Setup, Models & Routing

Hermes Agent has pushed over 17 trillion tokens through OpenRouter. Here's how to set it up, pick a model that clears the 64K context bar, and tune routing for cost and reliability.

June 12, 2026

How to Get the Lowest-Cost LLM Inference on OpenRouter

Append :floor for the cheapest provider, cap spend with max_price, and start free with 20+ zero-cost models. Plus the billing gotchas to avoid.

June 12, 2026

Gemini 2.5 Flash API - Pricing, Quickstart & Provider Comparison

Overpaying for reasoning you don't need? Learn how to configure Gemini 2.5 Flash API thinking budgets, compare providers, and make your first call in 5 minutes.

June 9, 2026

EU AI Act & Colorado ADMT Compliance: Human Oversight for AI Agents

Use the Agent SDK's human-in-the-loop (HITL) tools to meet AI agent compliance requirements from the EU AI Act, Colorado's Automated Decision-Making Technology law (SB26-189), and NIST AI RMF.

June 8, 2026

Human-in-the-Loop Tools for the Agent SDK

Human-in-the-loop tools in the OpenRouter Agent SDK let your agent auto-resolve routine decisions and pause for human input on high-stakes ones, with two hooks and zero loop-management code.

May 8, 2026

Agent SDK: Building Multi-turn Agent Workflows on OpenRouter

The OpenRouter Agent SDK gives you callModel: one function that turns a chat completion into a multi-step agent with tool calls, stop conditions, and cost tracking across 400+ models.

April 24, 2026

Build Your Own Harness with the Agent SDK

Use the create-agent-tui and create-headless-agent skills to scaffold a personalized coding agent in minutes — with a terminal UI or headless for scripts and pipelines.

April 24, 2026

Distillable Models and Synthetic Data Pipelines with NeMo Data Designer

How to generate license-safe synthetic data workflows for model specialization

December 24, 2025

Presets: How To Seamlessly Transfer Model Configurations Across Apps

Customize once and use everywhere. Server-side presets now simplify your model workflows.

July 29, 2025

Use OpenRouter Models in Cursor: Try it with Moonshot AI's Kimi K2

Explore it in action: See how effortlessly you can run Kimi K2 in Cursor using OpenRouter’s flexible model routing.

July 14, 2025