All Posts

Browse our complete archive of blog posts.

RSS

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

LLM Quantization: What fp8 and fp4 Do to Quality and Price

MCP vs CLI vs Skills: What Each Costs in Context

Best OCR Model for Scanned Documents, Measured

How to Build a Voice AI Agent

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

Introducing the New Auto and Auto Code Routers

Build an AI Code Reviewer with OpenRouter

How to Build Your Own Always-On AI Agent

Open-Weight vs Closed-Weight Models: What's the Difference?

How Much Does Claude Code Cost? Real Session Costs by Model

Claude Opus vs Sonnet vs Haiku: Which Should You Use?

Guardrails Now Separate Organization Limits from Workspace Defaults

How to Extract Tables from a PDF with an LLM

How to Prevent Prompt Injection: 13 Attacks, Tested

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

Hit Your Claude Code Usage Limit? How to Keep Coding

How we rebuilt provider routing for better, faster inference

CSAM Screening Across OpenRouter

Private Endpoints: Bring Your Fine-Tuned Models and Capacity to OpenRouter

ElevenLabs is now on OpenRouter

How an AI Sales Agent Saved Our Sales Team 600 Hours a Month

Server-Side Code Execution Tools for AI Agents, Compared

Agent Frameworks Compared: Tool-Calling Schema Handling

LangChain vs CrewAI: Orchestration Compared to OpenRouter-Native Routing

Model Router Benchmarks

Model Routing for Support Bots: Cheap-First FAQ Handling

Confidence Thresholds for Model Escalation Routing

Cost vs. Quality Tradeoff Framework for Agent Models

How to Gate Pull Requests on LLM Evals in CI

AI Agent Regression Testing After a Prompt or Model Change

Building a Golden Eval Dataset from Production Traffic

How to Test Tool-Calling Accuracy in AI Agents

Best Image-to-Video AI Models in 2026: Cost, Resolution, and Control

Manage and de-risk your API keys with new Security Center

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

Batch API: half-price inference by bundling requests

Is Jev as Accurate as Frontier Models at Classification?

What Is Nemotron 3.5 Lightning

Two Hours of Work That Takes a Week

Jev vs LLM-as-a-Judge

What Is Jev? TypeSafe's Decision Model Explained for Developers

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

Image Generation Models Compared: Cost, Edit, Quality

Build a Reliable Tool-Calling Agent Loop on OpenRouter

Does DeepSeek V4 Have Vision?

Case Study: How Descript Took New Models Off the Engineering Queue

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

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

Zero Data Retention (ZDR): What It Means for AI APIs

OpenRouter Fusion: How It Works and When to Use It

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

Nano Banana API: Edit Images with Gemini in Code

Seedance 2.5 Review: What It's Best At and When to Use It

In-Region Routing: Route inference in the US or EU

Give any model a terminal and files

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

GPT 5.6 Discounts & Jevons Paradox

OpenRouter Video Generation API: A Code-First Guide

Image Benchmarks: See the Capabilities of Every Model

OpenRouter is Joining Stripe

Understand your AI usage: every agent, model, and request

OpenRouter Image Generation: A Code-First API Tutorial

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

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

Live Web Search Benchmarks: Pick the Right Engine, Depth, and Model for Your Agent

Model Routing Powered by Wisdom of the Market

Set Up Team AI Spend Controls on OpenRouter

Governing AI Spend Across a Team on OpenRouter

Ori Harness: The Best Way to Use OpenRouter with Any Harness

Ori Eval: Find the Best Model for What You're Building

Using OpenRouter With LangChain: ChatOpenRouter Setup Guide

How to Evaluate LLM Provider Performance Across Latency, Throughput, and Uptime

Image Generation Models: Choosing One, Fixing Errors

Classifiers: Track What Your Agents Do and What It Costs

Transcription on OpenRouter

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

Every Modality Through One API

A New Look for OpenRouter

Why Use OpenRouter for DeepSeek

Choosing the Optimal Image Input Detail Level in LLMs

DeepSeek V4 Is Earning Agentic Token Share

The Open Weight Models that Matter: June 2026

The OpenRouter MCP Server

Introducing the Unified Image API

AI Governance Checklist: Your LLM Architecture Comes First

How to Enforce AI Data Residency Without Building Local Infrastructure

OpenRouter vs Portkey: Which LLM Gateway for Your Team?

OpenRouter vs LiteLLM: Which LLM Gateway Fits Your Stack?

Connect OpenClaw to OpenRouter

How to Connect SillyTavern to OpenRouter (2026 Guide)

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

How to Use OpenAI Codex CLI with OpenRouter

How to Use Claude Code with OpenRouter

How to Use OpenRouter With Any Coding Agent or AI Tool

Subagent: Let Your Model Delegate the Busywork

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

Agentic AI Governance: Your API Key Is a Guardrail

Keep Your Agent Running When Models Disappear

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

How to Get the Lowest-Cost LLM Inference on OpenRouter

How OpenRouter Model Routing Works

OpenRouter Reliability & Automatic Failover: How Requests Keep Succeeding

Surpassing Frontier Performance with Fusion

Dinner is Served

What Is an LLM Gateway? The Missing Layer Between Your App and AI Models

Advisor: Give Any Model a Lifeline to a Smarter One

Gemini 2.5 Flash API - Pricing, Quickstart & Provider Comparison

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

A Robot is Sprinting Towards You: Do You Want it Running on Claude or Grok?

May Release Spotlight

Guardrails: Protect your Agents, Data, and Costs

OpenRouter Raises $113M Series B

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

Consistent Web Search and Fetch Across Every Model

GPT-5.5 Price Increase: What It Actually Costs

New Audio APIs for Speech and Transcription

Response Caching: Zero Cost for Identical Requests

April Release Spotlight

Create OpenRouter Accounts via CLI with Stripe Projects

Opus 4.7's New Tokenizer: What It Actually Costs

Agent SDK: Building Multi-turn Agent Workflows on OpenRouter

Build Your Own Harness with the Agent SDK

Introducing Workspaces

Announcing Video Generation

Auto Exacto: Adaptive Quality Routing, On by Default

February Release Spotlight

OpenRouter Outages on February 17 and 19, 2026

January Release Spotlight

Distillable Models and Synthetic Data Pipelines with NeMo Data Designer

December Release Spotlight

Response Healing: Reduce JSON Defects by 80%+

The 2025 State of AI Report

Is Implicit Caching Prompt Retention?

Provider Variance: Introducing Exacto

October 2025 BYOK platform fee update

The First-Ever Image Model Is Up on OpenRouter

GPT-5 is now live

Audio Inputs and PDF URLs for Apps

Presets: How To Seamlessly Transfer Model Configurations Across Apps

New Privacy-Focused Provider Drop: Venice

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

Updates to Our Free Tier: Sustaining Accessible AI for Everyone

New Stealth Model: "Cypher Alpha"

Introducing Presets: Manage LLM Configs from Your Dashboard!

Dev & BYOK Updates: Uptime API + Smarter Key Management

Simplifying Our Platform Fee

GIF Prompts, Omni Search, Tool Caching, and BYOK Flags

New Features: Reasoning Streams, Crypto Invoices, End-User IDs & More

Passkeys, DevEx Upgrades, and a New Guide for TypeScript Agents

New Provider Drop: Cerebras Is Here

Better Insights, Faster Metrics, and New Developer Power Tools

Privacy Clarity, New Providers, OAuth Upgrade, and Gemini Gets Parallel Tools

Universal PDF Support

Smarter Charts, Inline SVGs, and Live Usage Accounting

Quasar Alpha and Optimus Alpha Reveal

"Stealth" model: Optimus Alpha

“Stealth” model: Quasar Alpha

Never Pay for Empty AI Responses Again

Deep Research & Many New Models

Introducing Nitro and Floor Price Shortcuts

Introducing Cloudflare as a new provider

Reasoning Tokens for Thinking Models

Introducing Web Search via the API

Standardized finish reasons

Happy New Year! Introducing a new Auto Router

Holiday launches: Web Search & Price Cuts

Bring Your Own API Keys

Crypto Payments API

Structured Outputs & Free Gemini Flash 2.0

Price Drops and Llama 3.3 70b

Author Pages & Amazon Nova

By subscribing you agree to receive the OpenRouter newsletter: model usage data, product updates, and research reports, about one email a week. Unsubscribe anytime via the link in every email. See our Privacy Policy.