Skip to content

LLM model pricing compared

Input and output pricing, context window, and tokenizer for all 11 OpenAI and Anthropic models, cheapest first. Rates are per million tokens and reflect promotional pricing where it applies.

ModelProviderInputOutputContext
GPT-4o miniOpenAI$0.15$0.60128K
GPT-5.6 LunaOpenAI$0.20$1.201,050K
GPT-3.5 TurboOpenAI$0.50$1.5016.385K
Claude Haiku 4.5Anthropic$1.00$5.00200K
GPT-5.6 TerraOpenAI$2.00$12.001,050K
GPT-4.1OpenAI$2.00$8.001,047.576K
GPT-4oOpenAI$2.50$10.00128K
Claude Sonnet 5Anthropic$2.00$10.001,000K
GPT-5.6 SolOpenAI$5.00$30.001,050K
Claude Opus 5Anthropic$5.00$25.001,000K
GPT-4 TurboOpenAI$10.00$30.00128K

Per-million rates are a starting point, not a bill. Several models charge more for the entire request once it crosses a long-context threshold — each model’s own page states whether that applies and at what point.