AI Tools
AI Model Comparator
Compare AI models side-by-side. See pricing, context windows, and capabilities.
| Feature | GPT-4o | GPT-4o Mini | Claude 3.5 Sonnet |
|---|---|---|---|
| Provider | OpenAI | OpenAI | Anthropic |
| Context Window | 128K | 128K | 200K |
| Input Price (per 1M tokens) | $2.50 | $0.15 | $3.00 |
| Output Price (per 1M tokens) | $10.00 | $0.60 | $15.00 |
| Max Output Tokens | 16K | 16K | 8K |
| Reasoning Mode | — | — | — |
| Multimodal | ✅ | ✅ | ✅ |
| Best For | General purpose, reasoning, code generation | General purpose, reasoning, code generation | Long documents, nuanced analysis, careful writing |
Pricing, context windows, and model list refresh live from OpenRouter's public model index.
Recommendations by Use Case
The Model Comparator lays today’s leading AI models side by side so you can pick the right one for the job — and for the budget.
Compare input and output pricing per million tokens, context window size, provider, and capabilities across GPT-4o, Claude, Gemini, DeepSeek, Llama, and others in a single table.
Prices and model data refresh live in your browser from OpenRouter’s public model index, so new releases and price cuts appear automatically — with a static fallback when you are offline.
Frequently Asked Questions
Where does the pricing data come from?
OpenRouter’s public model index, fetched directly by your browser. The page falls back to a built-in snapshot when you are offline.
How current is the pricing?
It refreshes each time you load the page, so price changes and newly released models show up without anyone editing the site by hand.
Which model should I choose?
There is no single best model. Routine tasks favour cheap fast models, long documents need large context windows, and complex reasoning benefits from frontier models — the table makes those trade-offs visible.