Sim is the open-source AI workspace where teams build, deploy, and manage AI agents. This page compares Claude Opus 5.5 and Claude Haiku 5.5 on API pricing per 1M tokens, context window, max output, and capabilities. Both models are available in the Sim Agent block, and each Agent block in a Sim agent can use a different model.
API model comparison
Claude Opus 5.5 vs Claude Haiku 5.5
Claude Haiku 5.5 is 40× cheaper than Claude Opus 5.5: 1,000 agent calls with 10k input and 1k output tokens each cost $1.5 versus $60 at standard rates.
Claude Opus 5.5 charges $4 input and $20 output per 1M tokens; Claude Haiku 5.5 charges $0.1 and $0.5.
Both models have a 1M token context window.
Both can generate up to 128k output tokens per response.
Both support configurable reasoning, tool choice control, and native structured outputs in Sim.
Pricing, context window, and capabilities
API prices are per 1M tokens. Pricing last updated .
| Metric | Claude Opus 5.5 | Claude Haiku 5.5 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Input price | $4/1M | $0.1/1M |
| Cached input | $0.2/1M | $0.01/1M |
| Output price | $20/1M | $0.5/1M |
| Long-context pricing | No long-context tier | Above 100k input tokens, the full request is priced at $0.5/1M input tokens, $0.05/1M cached input tokens, and $2.5/1M output tokens. |
| Context window | 1M tokens | 1M tokens |
| Released | Sep 22, 2026 | Oct 7, 2026 |
| Temperature | Not configurable | Not configurable |
| Reasoning effort | Not supported | Not supported |
| Verbosity | Not supported | Not supported |
| Thinking levels | low, medium, high, xhigh, max (default: medium) | low, medium, high, xhigh, max (default: medium) |
| Structured outputs | Supported (native) | Supported (native) |
| Tool choice | Supported | Supported |
| Computer use | Not supported | Not supported |
| Deep research | Not supported | Not supported |
| Memory support | Supported | Supported |
| Max output tokens | 128k | 128k |
Use Claude Opus 5.5 or Claude Haiku 5.5 in a Sim agent
Both models are available in the Sim Agent block. Pick either one from the model picker, and each Agent block in the same agent can use a different model.
Frequently asked questions
Claude Haiku 5.5 is 40× cheaper than Claude Opus 5.5: 1,000 agent calls with 10k input and 1k output tokens each cost $1.5 versus $60 at standard rates. Claude Opus 5.5 charges $4 input and $20 output per 1M tokens; Claude Haiku 5.5 charges $0.1 and $0.5.
