A Picture Is Still 1,200 Tokens: How Multimodal Inputs Get Billed in LLM APIs
OpenAI, Anthropic and Google each convert images, audio and video into input tokens by a different rule. The meter, not the per-million rate, decides the bill.

OpenAI, Anthropic and Google each convert images, audio and video into input tokens by a different rule. The meter, not the per-million rate, decides the bill.
