How GPT-6.2 Astra Is Priced: Short Context and Long Context Are Billed Separately

img-5492337be268411a00f1175b

Author’s note: Two worked-by-hand examples that make GPT-6.2 Astra’s short-context vs. long-context pricing clear, along with the multipliers for Batch, Fast, and Ultrafast. OpenAI released GPT-6.2 Astra and GPT-6.2 Sol on 2026-11-17, with model IDs gpt-6.2-astra and gpt-6.2-sol respectively. The short-context standard pricing on the official model page looks straightforward, but when it comes time … Read more

How GPT-6.2 Sol Is Priced: Input, Cache, and Output Are Calculated Separately

img-49d389b04a6a28cb155c8a1c

Author’s note: We break down gpt-6.2-sol’s four billing line items—input, cached read, cache write, and output—explain the whole-order algorithm that kicks in above 272K, walk through the Batch/Fast/Ultrafast multipliers, and work through two cost estimate examples: one for short contexts and one for extra-long contexts. OpenAI released GPT-6.2 Astra and GPT-6.2 Sol on November 17, … Read more