• gpt-5-nano — $0.05 / $0.40 per 1M tokens — the cheapest option here. Newest-generation lightweight model; worth checking reply quality holds up at this price for your questions.
• gpt-4.1-nano — $0.10 / $0.40 per 1M tokens — nearly as cheap as gpt-5-nano, previous generation. Useful side-by-side comparison at almost the same price.
• gpt-4o-mini — $0.15 / $0.60 per 1M tokens — the old live default before the gpt-5 switch. Still the cheapest well-tested option if cost ever needs to win over quality.
• gpt-5-mini — $0.25 / $2.00 per 1M tokens — newest-generation "mini" tier, noticeably stronger reasoning than the nano models for a moderate cost step up.
• gpt-4.1-mini — $0.40 / $1.60 per 1M tokens — previous-generation "mini" tier, comparable positioning to gpt-5-mini at a different input/output balance.
• gpt-5 — $1.25 / $10.00 per 1M tokens — the current live default for real visitors. Cheaper on input than gpt-4o despite being the newer, generally more capable model — best value at the top end.
• gpt-4.1 — $2.00 / $8.00 per 1M tokens — previous-generation flagship, strong general-purpose quality.
• gpt-4o — $2.50 / $10.00 per 1M tokens — the original flagship multimodal model, still widely used. The most expensive of the models recommended here.

Type or pick a model — the dropdown above is a short, recommended list for this kind of assistant (fast, cheap, general-purpose chat with occasional function calls), not every model this account can access. Any valid OpenAI model works if you type it in. Current pricing: platform.openai.com/docs/pricing