LLM API cost estimator

Set the inputs, then press Estimate.

• Input tokens are counted exactly, with the selected model's encoding. Output tokens are your number — the tool cannot predict a reply's length.
• Prices are a dated snapshot of the vendor's published per-1M rates (standard tier; documented long-context tiers applied above their boundary). Costs are exact BigInt arithmetic on those prices — no float rounding anywhere in a dollar figure.
• Not modeled, on purpose: cached-input discounts on your billed line (shown as a separate reference), batch rates, tool-call framing, and per-request platform fees where a provider charges them. A fake "efficiency" factor would just be lying with decimals.
• Prices change — the effective date ships with every result. Re-check the vendor page before committing a budget.

• gpt-5.6-sol$4 / $20
• gpt-5.6-terra$2 / $12
• gpt-5.6-luna$0.2 / $1.2
• gpt-5.6-cyber$12.5 / $75
• gpt-5.5$5 / $30
• gpt-5.5-pro$30 / $180
• gpt-5.4$2.5 / $15
• gpt-5.4-mini$0.75 / $4.5
• gpt-5.4-nano$0.2 / $1.25
• gpt-5.4-pro$30 / $180
• gpt-5.3-codex$1.75 / $14
• gpt-5.2$1.75 / $14
• gpt-5.2-pro$21 / $168
• gpt-5.1$1.25 / $10
• gpt-5$1.25 / $10
• gpt-5-mini$0.25 / $2
• gpt-5-nano$0.05 / $0.4
• gpt-5-pro$15 / $120
• gpt-4.1$2 / $8
• gpt-4.1-mini$0.4 / $1.6
• gpt-4.1-nano$0.1 / $0.4
• gpt-4o$2.5 / $10
• gpt-4o-mini$0.15 / $0.6
• o3$2 / $8
• o3-mini$1.1 / $4.4
• o3-pro$20 / $80
• o4-mini$1.1 / $4.4
• o1$15 / $60
• chat-latest$5 / $30
• gpt-4-turbo$10 / $30
• gpt-3.5-turbo$0.5 / $1.5