# Claude Opus 5 vs Claude Opus 5.5

As of October 21, 2026, Claude Opus 5 costs 25% more per input token than Claude Opus 5.5 ($5.00 vs $4.00 per 1M), and both have a 1M-token context window.

- Page: https://models.litellm.ai/compare/claude-opus-5-vs-claude-opus-5-5
- Claude Opus 5: https://models.litellm.ai/models/claude-opus-5
- Claude Opus 5.5: https://models.litellm.ai/models/claude-opus-5-5

## Side by side

| | Claude Opus 5 | Claude Opus 5.5 |
|---|---|---|
| Input, per 1M tokens | $5.00 | $4.00 |
| Output, per 1M tokens | $25.00 | $20.00 |
| Cache read, per 1M tokens | $0.50 | $0.20 |
| Cache write, per 1M tokens | $6.25 | $5.00 |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Max output | 128,000 tokens | 128,000 tokens |
| Image input | Yes | Yes |
| Tool calling | Yes | Yes |
| Structured output (JSON) | Yes | Yes |
| Prompt caching | Yes | Yes |
| Reasoning | Yes | Yes |
| Providers on LiteLLM | 9 | 8 |
| Price shown is from | Anthropic | Anthropic |
| Added to LiteLLM | July 24, 2026 | September 22, 2026 |

Headline prices in USD per 1M tokens, from LiteLLM's model price file.

## Cheapest provider for each

- Claude Opus 5: Anthropic at $5.00 input per 1M tokens (`claude-opus-5`)
- Claude Opus 5.5: Anthropic at $4.00 input per 1M tokens (`claude-opus-5-5`)

## Benchmark scores

| Benchmark | Claude Opus 5 | Claude Opus 5.5 |
|---|---|---|
| Epoch Capabilities Index (Overall) | 163.9 | 168.8 |
| FrontierCode (Coding and agents) | 53.4% (max) | 54.6% (medium) |
| FrontierSWE (Coding and agents) | 52.0% (max) | 62.3% (max) |
| APEX-Agents (Coding and agents) | 65.8% (max) | 73.5% (max) |
| GPQA Diamond (Reasoning and knowledge) | 93.9% (max) | 90.6% (max) |
| ARC-AGI-2 (Reasoning and knowledge) | 90.4% (max) | 93.3% (high) |
| SimpleQA Verified (Reasoning and knowledge) | 59.9% (max) | 72.2% (max) |
| FrontierMath (tiers 1-3) (Math) | 85.6% (max) | 91.2% (max) |
| FrontierMath (tier 4) (Math) | 73.2% (max) | 95.0% (max) |
| OTIS Mock AIME 2024-2025 (Math) | 98.9% (max) | 100.0% (max) |

From the Epoch AI Benchmarking Hub (https://epoch.ai/benchmarks), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), data as of September 22, 2026: Epoch's own runs and results it collects from each benchmark's leaderboard. Higher is better.

## When to pick which

- Claude Opus 5.5: Costs 20% less per input token: $4.00 vs $5.00 per 1M.

## FAQ

### Which is cheaper, Claude Opus 5 or Claude Opus 5.5?

Claude Opus 5.5 is cheaper at 3 input tokens per output token: $8.00 per 1M tokens blended ($4.00 input, $20.00 output), versus $10.00 ($5.00 and $25.00) for Claude Opus 5, as of October 21, 2026.

### Which has the larger context window, Claude Opus 5 or Claude Opus 5.5?

Both have a 1,000,000-token context window.

### Can I switch from Claude Opus 5 to Claude Opus 5.5 without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "claude-opus-5" to "claude-opus-5-5", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.