LLM Model Comparison
Compare Claude, GPT, and Gemini models side by side: context window, input/output pricing, and supported modalities. A quick reference for picking the right model for the job.
| Inputs | ||||
|---|---|---|---|---|
| Gemini 2.0 FlashGoogle | 1M | $0.1000 | $0.4000 | textimageaudiovideo |
| GPT-4o miniOpenAI | 128K | $0.1500 | $0.6000 | textimage |
| Gemini 2.5 FlashGoogle | 1M | $0.3000 | $2.50 | textimageaudiovideo |
| Claude Haiku 4.5Anthropic | 200K | $1.00 | $5.00 | textimage |
| o3-miniOpenAI | 200K | $1.10 | $4.40 | text |
| Gemini 2.5 ProGoogle | 1M | $1.25 | $10.00 | textimageaudiovideo |
| GPT-4oOpenAI | 128K | $2.50 | $10.00 | textimageaudio |
| Claude Sonnet 4.xAnthropic | 200K | $3.00 | $15.00 | textimage |
| Claude Opus 4.xAnthropic | 200K | $15.00 | $75.00 | textimage |
Prices per 1M tokens, list rates as of January 2026. Context in tokens. Specs change often — confirm with each provider before relying on them. Click a column to sort.
About LLM Model Comparison
Choosing a model means trading off price, context window, speed, and which inputs it accepts. This table lines up the major Claude, GPT, and Gemini models so you can compare per-million-token input and output pricing, how much context each holds, and whether it handles images, audio, or video — all in one place, sortable to whatever matters most for your use case.
Frequently asked questions
How current is this data?+
Specs and prices are captured as of the date noted on the page and change often. Always confirm against each provider's docs before committing.
What is a context window?+
It's the maximum number of tokens (prompt plus response) a model can consider at once. A bigger window lets you pass more documents or longer conversations.
Which model should I pick?+
Sort by what constrains you: cost for high volume, context window for long documents, or modalities if you need image/audio/video input. The cheapest capable model usually wins.