Inference
Long-context pricing
Higher per-token rates some providers charge when a single request exceeds a size threshold.
OpenAI charges more above 272K input tokens and Google above 200K on some models, while Anthropic includes the full 1M window at standard prices on current models. Check the threshold before sending very large documents.
Frequently asked questions
What does Long-context pricing mean?
Higher per-token rates some providers charge when a single request exceeds a size threshold. OpenAI charges more above 272K input tokens and Google above 200K on some models, while Anthropic includes the full 1M window at standard prices on current models. Check the threshold before sending very large documents.