15 models monitored across 4 providers. Every model pinged every 5 minutes.
Claude Opus 4.8
Anthropic's most capable model. Latest generation with sharper judgement, stronger agentic coding, and longer autonomous task runs.
Claude Sonnet 4.6
Anthropic's balanced model. Strong performance across coding, analysis, and creative tasks.
Claude Opus 4.7
Previous generation flagship. Still widely used for complex tasks.
Claude Haiku 4.5
Anthropic's fastest and most affordable model. Optimized for speed and cost efficiency.
GPT-4o
OpenAI's flagship multimodal model. Fast, capable, and widely used.
GPT-4o Mini
OpenAI's small and affordable model. Great for lightweight tasks.
GPT-4.1
OpenAI's latest generation model with improved coding and instruction following.
GPT-4.1 Mini
Compact version of GPT-4.1. Optimized for speed and cost.
o3
OpenAI's reasoning model. Thinks step-by-step before responding for complex problems.
o4-mini
OpenAI's compact reasoning model. Fast reasoning at lower cost.
Gemini 2.5 Flash
Google's fast model with strong multimodal capabilities and competitive throughput.
Gemini 2.5 Flash Lite
Google's fastest and cheapest model. Highest throughput of any major LLM API.
Gemini 2.5 Pro
Google's most capable reasoning model. Thinks before responding.