Compare API pricing across 30 AI models from providers like OpenAI, Anthropic, Google, Meta, and Mistral. Use the calculator above to estimate your monthly costs based on token usage volume and input/output ratio.
Most large language models charge per token — a unit roughly equal to ¾ of a word. Pricing is split into input tokens (your prompts) and output tokens (the model's responses). Output tokens are typically 2–4x more expensive than input tokens.
The cheapest model isn't always the best value. Consider the trade-off between cost and performance — a model with a higher benchmark score may save you money by requiring fewer retries and producing better results on the first attempt. Use our model comparison tool to evaluate performance alongside pricing.