Comparing 2
Browse all 30 models on the map or in the table.
Claude Opus 5.5vsClaude Haiku 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 Opus 5.5AnthropicNEW Claude model for long-running agentic coding and knowledge work | Claude Haiku 5.5AnthropicNEW Fast Claude model for responsive assistance, classification, and lightweight agents | |
|---|---|---|
| Intelligence | ||
| Intelligence index | 57.6 | 43.4 |
| Price | ||
| Input, $ per 1M | $4 | $0.10 |
| Output, $ per 1M | $20 | $0.50 |
| Typical message (500 in / 250 out) | $0.0070 | $0.00017 |
| Repeated input, cached | $0.20 · 20× cheaper | $0.01 · 10× cheaper |
| Prompts over 200K tokens | Same price | Same price |
| Limits | ||
| Context window | 1M | 1M |
| Longest answer | 128K tokens | 128K tokens |
| Knowledge cutoff | Jun 2026 | Jun 2026 |
| What it can take and do | ||
| Accepts | TextImagePDF | TextImagePDF |
| Reasoning effort | Low · Med · High · X-high · Max | Low · Med · High · X-high · Max |
| Tool use | Yes | Yes |
| Guaranteed JSON output | Yes | Yes |
| Availability | ||
| Released | 22 Sept 2026 | 7 Oct 2026 |
| Open weights | No | No |
| API providers offering it | 36 | 33 |