Sim is the open-source AI workspace where teams build, deploy, and manage AI agents. This page compares Claude Haiku 5.5 and GPT-6 Luna 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 Haiku 5.5 vs GPT-6 Luna
Claude Haiku 5.5 and GPT-6 Luna cost about the same: 1,000 agent calls with 10k input and 1k output tokens each cost $1.5 and $1.5 at standard rates.
Claude Haiku 5.5 charges $0.1 input and $0.5 output per 1M tokens; GPT-6 Luna charges $0.1 and $0.5.
Their context windows are about the same size: 1M versus 1.05M tokens.
Both can generate up to 128k output tokens per response.
Only Claude Haiku 5.5 supports native structured outputs in Sim.
Pricing, context window, and capabilities
API prices are per 1M tokens. Pricing last updated .
| Metric | Claude Haiku 5.5 | GPT-6 Luna |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Input price | $0.1/1M | $0.1/1M |
| Cached input | $0.01/1M | $0.01/1M |
| Output price | $0.5/1M | $0.5/1M |
| Long-context pricing | 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. | Above 272k input tokens, the full request is priced at $0.2/1M input tokens, $0.02/1M cached input tokens, and $0.75/1M output tokens. |
| Context window | 1M tokens | 1.05M tokens |
| Released | Oct 7, 2026 | Sep 22, 2026 |
| Temperature | Not configurable | Not configurable |
| Reasoning effort | Not supported | none, low, medium, high, xhigh, max |
| Verbosity | Not supported | low, medium, high |
| Thinking levels | low, medium, high, xhigh, max (default: medium) | Not supported |
| Structured outputs | Supported (native) | Supported |
| 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 Haiku 5.5 or GPT-6 Luna 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 and GPT-6 Luna cost about the same: 1,000 agent calls with 10k input and 1k output tokens each cost $1.5 and $1.5 at standard rates. Claude Haiku 5.5 charges $0.1 input and $0.5 output per 1M tokens; GPT-6 Luna charges $0.1 and $0.5.
