Claude Opus 5.5 vs Claude Sonnet 5.5
Official Anthropic API prices and LMArena scores, checked 2026-10-18. Add up to 2 more models to compare 4.
Claude Sonnet 5.5 costs less; Claude Opus 5.5 wins more LMArena tasks.
Claude Sonnet 5.5 is 2x cheaper on input and output. Claude Opus 5.5 scores 73 points higher for creative writing. Across 7 shared LMArena tasks, Claude Opus 5.5 leads 6 to 0 (1 tied). A medium month (20M input + 5M output tokens) costs $180 on Claude Opus 5.5 and $90 on Claude Sonnet 5.5.
- Pick Claude Opus 5.5 if you care most about creative writing (+73), chat (+58) and vision (+58).
- Pick Claude Sonnet 5.5 if you want the lower bill ($90 vs $180 for a medium month).
Medium: 20M input + 5M output tokens a month at list price (short-context rate, no caching or batch discounts).
Marked side is better: lower for prices, higher for context and scores. Bars are scaled to the larger of the two.
| Spec | Claude Opus 5.5 | Claude Sonnet 5.5 |
|---|---|---|
| Price per 1M tokens | ||
| Input | $4 | $2 |
| Cached input | $0.20 | None |
| Output | $20 | $10 |
| Blend 3:1 | $8 | $4 |
| Sample month, medium | $180 | $90 |
| Context | ||
| Context window | 1M tokens | 1M tokens |
| Quality (LMArena, out of 100) | ||
| Coding | 100/100 #1 of 23 | 86/100 #3 of 23 |
| Chat | 72/100 #3 of 25 | 14/100 #14 of 25 |
| Creative writing | 100/100 #1 of 25 | 27/100 #10 of 25 |
| Roleplay and characters | 34/100 #4 of 25 | 0/100 #15 of 25 |
| Reasoning and math | 53/100 #6 of 24 | 53/100 #7 of 24 |
| Vision | 82/100 #3 of 21 | 24/100 #14 of 21 |
| Long documents | Not ranked | Not ranked |
| Cheap bulk and agents | 100/100 #1 of 23 | 82/100 #6 of 23 |
| Details | ||
| Provider | Anthropic | Anthropic |
| API model id | claude-opus-5.5 | claude-sonnet-5.5 |
| Notes | 5-minute cache writes $5. | 5-minute cache writes $2.50. |
| Sources | ||
| Last checked | 2026-10-18 | 2026-10-18 |
| Official pricing | Anthropic pricing | Anthropic pricing |
Plans from data checked hourly against each vendor's official pricing page. Vendors state limits in different units, so we quote them as published. Team and enterprise plans are per seat.
API prices in USD per 1M tokens from each provider's official pricing page. Blend 3:1 = (3 x input + output) / 4. Sample month = stated input and output tokens at the list price, no caching. Quality: relative score out of 100 on each LMArena leaderboard (100 = top model we price on that board, n/a = not ranked there), data licensed CC BY 4.0. See how we pick.
Where each one ranks on LMArena
Relative score out of 100 on each leaderboard (100 = the top model we price there), with the rank among the models from our API price table that appear on that board.
- Coding (Code Arena): Claude Opus 5.5 #1 of 23 (100/100), Claude Sonnet 5.5 #3 of 23 (86/100)
- Chat (Text Arena): Claude Opus 5.5 #3 of 25 (72/100), Claude Sonnet 5.5 #14 of 25 (14/100)
- Creative writing (Text Arena creative writing): Claude Opus 5.5 #1 of 25 (100/100), Claude Sonnet 5.5 #10 of 25 (27/100)
- Roleplay and characters (Text Arena multi-turn): Claude Opus 5.5 #4 of 25 (34/100), Claude Sonnet 5.5 #15 of 25 (0/100)
- Reasoning and math (Text Arena math): Claude Opus 5.5 #6 of 24 (53/100), Claude Sonnet 5.5 #7 of 24 (53/100)
- Vision (Vision Arena): Claude Opus 5.5 #3 of 21 (82/100), Claude Sonnet 5.5 #14 of 21 (24/100)
- Long documents (Document Arena): Claude Opus 5.5 not ranked, Claude Sonnet 5.5 not ranked
- Cheap bulk and agents (Agent Arena): Claude Opus 5.5 #1 of 23 (100/100), Claude Sonnet 5.5 #6 of 23 (82/100)
Pricing details from the official pages
Claude Opus 5.5 lists $4 input, $20 output, $0.20 cached input per 1M tokens on Anthropic pricing. Claude Sonnet 5.5 lists $2 input, $10 output per 1M tokens on Anthropic pricing. Prices checked 2026-10-18.
- Claude Opus 5.5: 5-minute cache writes $5.
- Claude Sonnet 5.5: 5-minute cache writes $2.50.
Sample monthly bill at list price, no caching: Light (2M input + 0.5M output tokens): $18 vs $9. Medium (20M input + 5M output tokens): $180 vs $90. Heavy (200M input + 50M output tokens): $1,800 vs $900.
FAQ
Is Claude Opus 5.5 cheaper than Claude Sonnet 5.5?
Claude Opus 5.5 costs $4 input and $20 output per 1M tokens; Claude Sonnet 5.5 costs $2 and $10. For a medium month (20M input + 5M output tokens) Claude Sonnet 5.5 is cheaper: $90 vs $180.
Which is better for coding, Claude Opus 5.5 or Claude Sonnet 5.5?
On LMArena's Code Arena Claude Opus 5.5 scores 100/100 (#1 of 23) and Claude Sonnet 5.5 86/100 (#3 of 23), so Claude Opus 5.5 is ahead by 14 points.
Which has the bigger context window?
Claude Opus 5.5: 1M tokens. Claude Sonnet 5.5: 1M tokens. Both list the same window.
How much do Claude Opus 5.5 and Claude Sonnet 5.5 cost per month?
Light (2M input + 0.5M output tokens): $18 vs $9. Medium (20M input + 5M output tokens): $180 vs $90. Heavy (200M input + 50M output tokens): $1,800 vs $900. Pick your own token counts in the plan vs API calculator.
Where do these numbers come from?
Prices come from each provider's official pricing page, checked daily. Quality is the relative score on the LMArena leaderboard dataset, licensed CC BY 4.0. Where a model is not ranked we show n/a.