# Claude Haiku 5.5 vs Sonar Pro - AI Model Comparison

- Page: https://opencode.ai/data/compare/anthropic/claude-haiku-5-5/perplexity/sonar-pro
- Updated: 2026-10-07T20:48:51.000Z

|  | Claude Haiku 5.5 | Sonar Pro |
| --- | --- | --- |
| Lab | Anthropic | Perplexity |
| Context window | 1M | 200K |
| Max output | 128K | 8.2K |
| Input modalities | text, image, pdf | text, image |
| Reasoning | Yes | No |
| Tool calling | Yes | No |
| Open weights | No | No |
| Release date | 2026-10-07 | 2024-01-01 |
| Input price per 1M tokens | $0.10 | $3.00 |
| Output price per 1M tokens | $0.50 | $15.00 |
| Cached input price per 1M tokens | $0.01 | - |
| OpenCode tokens: past 2 months | 352M | - |
| Share of all tokens | 0% | - |
| Rank by tokens last week | #43 | - |
| Unique users | 176 | - |
| Weekly retention | - | - |

Model pages: [Claude Haiku 5.5](https://opencode.ai/data/anthropic/claude-haiku-5-5.md), [Sonar Pro](https://opencode.ai/data/perplexity/sonar-pro.md)

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.