Comparing 3
Browse all 30 models on the map or in the table.
Claude Haiku 5.5vsClaude Sonnet 5.5vsClaude Opus 5.5
Send one prompt to every model and read the answers side by side, with speed and cost for each.
Shareable link:
Before you run
Highlighted values are the best among your picks.
Claude Haiku 5.5AnthropicNEW Fast Claude model for responsive assistance, classification, and lightweight agents | Claude Sonnet 5.5AnthropicNEW Fast Claude model for everyday coding, agents, and knowledge work | Claude Opus 5.5AnthropicNEW Claude model for long-running agentic coding and knowledge work | |
|---|---|---|---|
| Intelligence | |||
| Intelligence index | 43.4 | 56 | 57.6 |
| Price | |||
| Input, $ per 1M | $0.10 | $2 | $4 |
| Output, $ per 1M | $0.50 | $10 | $20 |
| Typical message (500 in / 250 out) | $0.00017 | $0.0035 | $0.0070 |
| Repeated input, cached | $0.01 · 10× cheaper | $0.10 · 20× cheaper | $0.20 · 20× cheaper |
| Prompts over 200K tokens | Same price | Same price | Same price |
| Limits | |||
| Context window | 1M | 1M | 1M |
| Longest answer | 128K tokens | 128K tokens | 128K tokens |
| Knowledge cutoff | Jun 2026 | Jun 2026 | Jun 2026 |
| What it can take and do | |||
| Accepts | TextImagePDF | TextImagePDF | TextImagePDF |
| Reasoning effort | Low · Med · High · X-high · Max | Low · Med · High · X-high · Max | Low · Med · High · X-high · Max |
| Tool use | Yes | Yes | Yes |
| Guaranteed JSON output | Yes | Yes | Yes |
| Availability | |||
| Released | 7 Oct 2026 | 28 Sept 2026 | 22 Sept 2026 |
| Open weights | No | No | No |
| API providers offering it | 33 | 34 | 36 |