Most cost-efficient Gemini paid tier in the current pricing page.

Input price uses cache miss reference from current docs.

Standard paid-tier pricing; output includes thinking tokens.

Smaller model focused on lower cost and fast tool workflows.

Lowest-latency Claude family option in the official table.

Short-input pricing reference from the Gemini pricing page.

Higher-capability tier from the official pricing table.

Balanced flagship coding and professional work model.

Mainstream Claude coding and analysis tier.

Standard processing rate from the official API pricing page.

Official model pricing table reference.