Sim is the open-source AI workspace where teams build, deploy, and manage AI agents. This page compares GPT-5.4 and GPT-5.4 Mini 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
GPT-5.4 vs GPT-5.4 Mini
GPT-5.4 Mini is 3.3× cheaper than GPT-5.4: 1,000 agent calls with 10k input and 1k output tokens each cost $12 versus $40 at standard rates.
GPT-5.4 charges $2.5 input and $15 output per 1M tokens; GPT-5.4 Mini charges $0.75 and $4.5.
GPT-5.4 has a 2.6× larger context window: 1.05M versus 400k tokens.
Both can generate up to 128k output tokens per response.
Both support configurable reasoning and tool choice control in Sim.
Pricing, context window, and capabilities
API prices are per 1M tokens. Pricing last updated .
| Metric | GPT-5.4 | GPT-5.4 Mini |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Input price | $2.5/1M | $0.75/1M |
| Cached input | $0.25/1M | $0.075/1M |
| Output price | $15/1M | $4.5/1M |
| Long-context pricing | Above 272k input tokens, the full request is priced at $5/1M input tokens, $0.5/1M cached input tokens, and $22.5/1M output tokens. | No long-context tier |
| Context window | 1.05M tokens | 400k tokens |
| Released | Mar 5, 2026 | Mar 17, 2026 |
| Temperature | Not configurable | Not configurable |
| Reasoning effort | none, low, medium, high, xhigh | none, low, medium, high, xhigh |
| Verbosity | low, medium, high | low, medium, high |
| Thinking levels | Not supported | Not supported |
| Structured outputs | Supported | 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 GPT-5.4 or GPT-5.4 Mini 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
GPT-5.4 Mini is 3.3× cheaper than GPT-5.4: 1,000 agent calls with 10k input and 1k output tokens each cost $12 versus $40 at standard rates. GPT-5.4 charges $2.5 input and $15 output per 1M tokens; GPT-5.4 Mini charges $0.75 and $4.5.
