The AI model landscape changes weekly. OpenRouter aggregates 100+ models from every major provider — OpenAI, Anthropic, Google, Meta, Mistral, Cohere, and dozens of open-source projects — into a single API. This dashboard lets you compare them all side-by-side on the metrics that matter: cost per token, context window size, throughput speed, and quality benchmarks. Whether you're building a chatbot, processing documents, or running inference at scale, find the right model at the right price.
100+ models are available on OpenRouter from 50+ providers as of June 2026. This includes models from OpenAI (GPT-4o, o3), Anthropic (Claude Opus 4, Sonnet 4), Google (Gemini 2.5), Meta (Llama 4), and dozens of open-source alternatives.
$0.10 per million tokens is the floor price for lightweight models like Llama 4 Scout and Mistral Small. Premium models like Claude Opus 4 and GPT-4o range from $3-$15 per million input tokens. The dashboard lets you sort by cost to find the best value for your use case.
1M tokens is the largest context window available, offered by Google Gemini 2.5 Pro and Anthropic Claude models. Most GPT-4 class models support 128K tokens. The dashboard tracks context window sizes across all providers so you can filter by your document processing needs.
200+ tokens per second is achievable with optimized smaller models like Claude Haiku and GPT-4o Mini. Larger reasoning models like o3 and Claude Opus 4 trade speed for accuracy at 30-80 tokens per second. The dashboard benchmarks throughput across all available models.
Pricing and availability data updates in real time via the OpenRouter API. New models are typically added within 24 hours of their release on the platform. The dashboard has tracked 50+ model launches in 2026 alone.