Skip to guides

Understand your
AI coding costs.

Published rates, worked examples, and local usage. Start with a model’s pricing, then look at the repositories and sessions behind the tokens.

GPT-6.1 Terra Pricing and 12-Hour Cache Writes

GPT-6.1 Terra input, cached input, cache-write, and output prices explained, including 30-minute and 12-hour writes, with a worked estimate and local Codex usage tracking.

Snapshots GPT-6.1 Terra at $1 input, $0.05 cached input, and $5 output per million tokens, explains the new 30-minute and 12-hour cache-write lifetimes, and shows where RepoSpend reads the same Codex usage locally.

Read guide →

GPT-6.1 Sol Pricing and Codex Cost Tracking

GPT-6.1 Sol input, cached input, cache-write, and output prices explained, with a worked estimate and local Codex usage tracking by repository.

Snapshots GPT-6.1 Sol at $2 input, $0.10 cached input, and $10 output per million tokens, applies them in a worked estimate, and shows where RepoSpend reads the same Codex usage locally.

Read guide →

AI Coding Price Guide: Claude 5.5 vs GPT-6.1 Sol

Compare current Claude and GPT API prices, including cache reads and Haiku 5.5 prompt-length tiers, with context on coding-task cost.

Side-by-side rate cards for nine current GPT-6 and Claude models — including new GPT-6.1 Terra, Claude Fable 5.1, and Mythos 5.1 (restricted availability) — every row linked to the vendor pricing page it came from.

Read guide →

API-equivalent estimates help compare usage. They do not represent subscription invoices or independently verified task success.

Estimate one authored workload or API request. Compare model prices in the browser calculator →