GPT-5.4 Nano is the smallest and fastest model in the GPT-5.4 family. At $0.20 per million input tokens, it’s built for high-volume workloads where speed and cost matter more than peak reasoning. Reach for it when you need quick classification, extraction, ranking, or lightweight coding support.

Strengths

  • Fastest model in the GPT-5.4 lineup. Ideal for latency-sensitive tasks and tight agentic loops.
  • $0.20/1M input tokens. One of the cheapest options available. Strong for high-volume pipelines and subagent work.
  • Good at structured tasks. Classification, extraction, ranking, and simple code edits land reliably.
  • Supports tool use. Can drive agent workflows, though best paired with a larger planning model for complex multi-step work.

Limitations

  • Not designed for deep reasoning or large-scale code generation. Stick with GPT-5.4 Mini or GPT-5.4 for harder problems.
  • Trades capability for speed. Expect lower quality on open-ended or ambiguous tasks.

Tools

GPT-5.4 Nano has access to all agent tools when used with Cursor including:

Learn more about how tools work and tool calling fundamentals.

Pricing

Cursor plans include two usage pools. GPT-5.4 Nano draws from the third-party Other Models pool, which charges at the rates below. All prices are per million tokens.