Compare models
Up to 4 models side by side: list prices, what a month of real traffic costs, limits and capabilities. The best value in each row is marked with a check.
| Model | ||
|---|---|---|
| Overview | ||
| Released | 19 Mar 2025 | 22 Sep 2026 |
| Status | Older Newer: o3-pro | Current |
| Open weights | No | No |
| Hosts APIs you can call it on | 1 | 9 |
| Price · USD per million tokens, at the lab's own API where it sells the model | ||
| Priced at | OpenAI | Anthropic |
| Input | $150.00 | $4.00 |
| Output | $600.00 | $20.00 |
| Cached input | - | $0.20 |
| Batch input / output | $75.00 / $300.00 | $2.00 / $10.00 |
| Cheapest anywhere input / output | $150.00 / $600.00 OpenAI | $4.00 / $20.00 Anthropic |
| Monthly bill · at the price above, 30 days, with each workload's cache and batch use | ||
| Chat assistant 5,000 a day, 2K in, 500 out | $90,000 | $2,358 |
| RAG over documents 2,000 a day, 8K in, 600 out | $93,600 | $1,728 |
| Coding agent 1,000 a day, 40K in, 2K out | $216,000 | $2,808 |
| Overnight batch 20,000 a day, 4K in, 400 out | $252,000 | $7,200 |
| Limits | ||
| Context window | 200K tokens | 1M tokens |
| Max output | 100K tokens | 128K tokens |
| Capabilities | ||
| Takes in | Images, Text, PDFs | Text, Images, PDFs |
| Produces | Text | Text |
| Effort settings as listed by the source | - | xhigh, max |
| Streaming | ||
| Function calling | ||
| JSON mode | ||
| Structured outputs | ||
| Reasoning | ||
| Tool calling | ||
| Prompt caching | ||
| Batch API | ||
| Adaptive thinking | ||
| Always reasons | ||
| Built-in web search | ||
| Computer use | ||
| Fast mode | ||
| Native structured output | ||
| Parallel tool calls | ||