Claude Sonnet 5.5 vs Claude Haiku 5.5
Official Anthropic API prices and LMArena scores, checked 2026-10-29. Add up to 2 more models to compare 4.
Claude Haiku 5.5 costs less; Claude Sonnet 5.5 wins more LMArena tasks.
Claude Haiku 5.5 is 20x cheaper on input and output. Claude Sonnet 5.5 scores 67 points higher for coding. Across 6 shared LMArena tasks, Claude Sonnet 5.5 leads 6 to 0. A medium month (20M input + 5M output tokens) costs $90 on Claude Sonnet 5.5 and $4.50 on Claude Haiku 5.5.
- Pick Claude Sonnet 5.5 if you care most about coding (+67), reasoning and math (+57) and agent tasks (+32).
- Pick Claude Haiku 5.5 if you want the lower bill ($4.50 vs $90 for a medium month) or you reuse long prompts (cached input $0.01 vs $0.10).
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 Sonnet 5.5 | Claude Haiku 5.5 |
|---|---|---|
| Price per 1M tokens | ||
| Input | $2 | $0.10 |
| Cached input | $0.10 | $0.01 |
| Output | $10 | $0.50 |
| Blend 3:1 | $4 | $0.20 |
| Sample month, medium | $90 | $4.50 |
| Context | ||
| Context window | 1M tokens | 1M tokens |
| Quality (LMArena, out of 100) | ||
| Coding | 85/100 #3 of 50 | 18/100 #24 of 50 |
| Chat | 18/100 #16 of 51 | 0/100 #45 of 51 |
| Creative writing | 31/100 #10 of 51 | 0/100 #47 of 51 |
| Roleplay and characters | 1/100 #17 of 51 | 0/100 #45 of 51 |
| Reasoning and math | 57/100 #8 of 51 | 0/100 #34 of 51 |
| Vision | 22/100 #16 of 33 | Not ranked |
| Long documents | Not ranked | Not ranked |
| Cheap bulk and agents | 81/100 #2 of 34 | 49/100 #17 of 34 |
| Details | ||
| Provider | Anthropic | Anthropic |
| API model id | claude-sonnet-5.5 | claude-haiku-5.5 |
| Notes | 5-minute cache writes $2.50. | Prompts up to 100K tokens. Longer prompts cost $0.50 in, $2.50 out. 5-minute cache writes $0.125. |
| Sources | ||
| Last checked | 2026-10-29 | 2026-10-29 |
| 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 Sonnet 5.5 #3 of 50 (85/100), Claude Haiku 5.5 #24 of 50 (18/100)
- Chat (Text Arena): Claude Sonnet 5.5 #16 of 51 (18/100), Claude Haiku 5.5 #45 of 51 (0/100)
- Creative writing (Text Arena creative writing): Claude Sonnet 5.5 #10 of 51 (31/100), Claude Haiku 5.5 #47 of 51 (0/100)
- Roleplay and characters (Text Arena multi-turn): Claude Sonnet 5.5 #17 of 51 (1/100), Claude Haiku 5.5 #45 of 51 (0/100)
- Reasoning and math (Text Arena math): Claude Sonnet 5.5 #8 of 51 (57/100), Claude Haiku 5.5 #34 of 51 (0/100)
- Vision (Vision Arena): Claude Sonnet 5.5 #16 of 33 (22/100), Claude Haiku 5.5 not ranked
- Long documents (Document Arena): Claude Sonnet 5.5 not ranked, Claude Haiku 5.5 not ranked
- Cheap bulk and agents (Agent Arena): Claude Sonnet 5.5 #2 of 34 (81/100), Claude Haiku 5.5 #17 of 34 (49/100)
Pricing details from the official pages
Claude Sonnet 5.5 lists $2 input, $10 output, $0.10 cached input per 1M tokens on Anthropic pricing. Claude Haiku 5.5 lists $0.10 input, $0.50 output, $0.01 cached input per 1M tokens on Anthropic pricing. Prices checked 2026-10-29.
- Claude Sonnet 5.5: 5-minute cache writes $2.50.
- Claude Haiku 5.5: Prompts up to 100K tokens. Longer prompts cost $0.50 in, $2.50 out. 5-minute cache writes $0.125.
Sample monthly bill at list price, no caching: Light (2M input + 0.5M output tokens): $9 vs $0.45. Medium (20M input + 5M output tokens): $90 vs $4.50. Heavy (200M input + 50M output tokens): $900 vs $45.
FAQ
Is Claude Sonnet 5.5 cheaper than Claude Haiku 5.5?
Claude Sonnet 5.5 costs $2 input and $10 output per 1M tokens; Claude Haiku 5.5 costs $0.10 and $0.50. For a medium month (20M input + 5M output tokens) Claude Haiku 5.5 is cheaper: $4.50 vs $90.
Which is better for coding, Claude Sonnet 5.5 or Claude Haiku 5.5?
On LMArena's Code Arena Claude Sonnet 5.5 scores 85/100 (#3 of 50) and Claude Haiku 5.5 18/100 (#24 of 50), so Claude Sonnet 5.5 is ahead by 67 points.
Which has the bigger context window?
Claude Sonnet 5.5: 1M tokens. Claude Haiku 5.5: 1M tokens. Both list the same window. Long prompts can cost more; see the pricing notes above.
How much do Claude Sonnet 5.5 and Claude Haiku 5.5 cost per month?
Light (2M input + 0.5M output tokens): $9 vs $0.45. Medium (20M input + 5M output tokens): $90 vs $4.50. Heavy (200M input + 50M output tokens): $900 vs $45. 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.
Sources
Related
- Cheapest LLM APIs, compared
- Anthropic API pricing, every model
- GPT-6.1 Sol vs Claude Sonnet 5.5
- Claude Opus 5.5 vs Claude Sonnet 5.5
- Claude Haiku 5.5 vs Gemini 3.8 Flash
- Claude Sonnet 5.5 vs Gemini 4 Argon
- GPT-6.1 Terra vs Claude Sonnet 5.5
- GLM-5.3 vs Claude Sonnet 5.5
- MiniMax-M3 vs Claude Sonnet 5.5
- DeepSeek V4.1 Flash vs Claude Haiku 5.5