Claude 3 Opus vs Claude 4.1 Opus Thinking (32K)
Claude 3 Opus is cheaper on output tokens. Choose Claude 3 Opus or Claude 4.1 Opus Thinking (32K) based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Claude 3 Opus | Claude 4.1 Opus Thinking (32K) |
|---|---|---|
| Provider | LLM Gateway | NanoGPT |
| Input / 1M tokens | $15.00 | $14.99 |
| Output / 1M tokens | $75.00 | $75.00 |
| Context window | 200K | 200K |
| Parameters | — | — |
| Open weights | No | No |
| Released | Mar 2024 | May 2025 |
| SWE-bench Verified score | 15.8 | — |
| LMArena (Chatbot Arena) Elo score | 1262 | — |
| LMArena Vision Elo score | 1023 | — |
| GPQA Diamond score | 47.2 | — |
| Epoch Capabilities Index score | 127 | — |
| LiveBench score | — | 61.4 |
FAQ
Is Claude 3 Opus or Claude 4.1 Opus Thinking (32K) cheaper?
Claude 3 Opus is cheaper on output tokens ($75.00 vs $75.00 per 1M).
Which has the larger context window, Claude 3 Opus or Claude 4.1 Opus Thinking (32K)?
Both models offer a similar context window.
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.