Unified API for 200+ models. One API key, one billing dashboard. OpenAI, Anthropic, Google, Meta, Mistral, and more. Automatic fallbacks and load balancing.
OpenRouter gives you a single API endpoint to access every major AI model - OpenAI (GPT-4o, o3), Anthropic (Claude), Google (Gemini), Meta (Llama), Mistral, and 200+ more. One API key, unified billing, automatic fallbacks if a provider is down. It's essential for comparing models without managing multiple API keys and billing accounts. I use it when I need to quickly swap between models for testing or when building apps that should work across providers.
Anthropic's AI. Opus 4.6 for hard problems, Sonnet 4.6 for speed, Haiku 4.5 for cost. 200K context window. Best coding model I've tested. Max plan ($200/mo).
OpenAI's flagship. GPT-4o for general use, o3 for reasoning, Codex for coding. 300M+ weekly users. Tasks, agents, web browsing, DALL-E, code interpreter.
Open-source reasoning models from China. DeepSeek-R1 rivals o1 on math and code benchmarks. V3 for general use. Fully open weights. Extremely cost-effective API.
Meta's open-source model family. Llama 4 available in Scout (17B active) and Maverick (17B active, 128 experts). Free to use, modify, and deploy commercially.
Unified API for 200+ models. One API key, one billing dashboard. OpenAI, Anthropic, Google, Meta, Mistral, and more. Automatic fallbacks and load balancing.
Try OpenRouterHonest takes on AI dev tools, frameworks, and infrastructure - delivered to your inbox.
Subscribe FreeAnthropic's AI. Opus 4.6 for hard problems, Sonnet 4.6 for speed, Haiku 4.5 for cost. 200K context window. Best coding model I've tested. Max plan ($200/mo).
OpenAI's flagship. GPT-4o for general use, o3 for reasoning, Codex for coding. 300M+ weekly users. Tasks, agents, web browsing, DALL-E, code interpreter.
Open-source reasoning models from China. DeepSeek-R1 rivals o1 on math and code benchmarks. V3 for general use. Fully open weights. Extremely cost-effective API.
Install Ollama and LM Studio, pull your first model, and run AI locally for coding, chat, and automation - with zero cloud dependency.
Getting StartedUse opus, sonnet, haiku, and best to switch models easily.
Claude CodeAdd gateway or custom models to the picker via environment variables.
Claude Code
GitHub Models is fully retired as of July 30, 2026. The playground, model catalog, inference API, and BYOK are gone for...

A hands-on developer guide to Mercury 2 from Inception Labs. OpenAI-compatible API, reasoning levels, tool use, structur...

AI2 released TutorMoments, a replay-based benchmark that drops seven LLMs into real math tutoring transcripts and scores...

The 7 AI developer stories that actually mattered this week - ranked, linked, and cut for builders.

A final Digital Markets Act decision requires Alphabet to give third-party AI assistants the same Android access Gemini...

How much of an AI session can you actually take with you? Store defaults, encrypted reasoning, opaque compaction, hidden...

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.