Model Comparison Matrix
Here is a quick cheat sheet comparing different model families for context loading:
| Model | Context Window | Input Cost ($/M) | Output Cost ($/M) | Strengths |
|---|---|---|---|---|
| Claude 3.5 Sonnet | 200k | $3.00 | $15.00 | Coding, visual reasoning, tool use |
| GPT-4o | 128k | $5.00 | $15.00 | Multimodality, general knowledge |
| Gemini 1.5 Pro | 2M | $7.00 | $21.00 | Massive context, multimodal search |