LLM Model Comparison
The leading Claude, GPT, and Gemini models side by side: context window, API pricing, modality, relative speed, and what each one is actually best at. Click any column header to sort; filter by tier.
Curated as of July 2026. Prices are USD per 1M tokens. Non-Claude figures are approximate - always verify on the provider's pricing page before budgeting.
How to choose: start from the cheapest tier that could plausibly do your task, and only move up when your evals say quality is insufficient. Fast-tier models (Haiku 4.5, GPT-5.5 mini, Gemini 3 Flash) handle classification, extraction, and routing at a tiny fraction of frontier cost; frontier models earn their price on hard reasoning, complex agents, and high-stakes output. A common production pattern is a router: fast model by default, escalate to a frontier model when confidence is low. All figures are approximate, as of July 2026 - check each provider's official pricing and docs before committing (models and prices change often). See the LLM Price Calculator to estimate monthly costs for your workload.