GPT-6.1 Terra API pricing & cost

Current GPT-6.1 Terra API pricing, cached input, long-context rules and workload calculators.

Calculate my workload →Official source ↗

Current rates

Pricing snapshot

Static catalog entry updated November 9, 2026; live provider registry data replaces matching rates on load when available.

Input / 1M tokens$1

Output / 1M tokens$5

Cached input / 1M$0.05

Context window1.05M tokens

Model facts

Pricing rules and quick cost example

What is tracked

1,050,000-token context window and 128,000 max output tokens.
Cached input is 5% of the standard input rate.
Prompts above 272K input tokens use 2× input/cache and 1.5× output rates.
Batch and Flex processing are 50% below Standard rates.

2K input + 500 output tokens

At current standard text-token rates, one request is about $0.0045; 1,000 requests ≈ $4.50, before tool fees, regional uplifts or special processing modes.

Use your workload

Turn GPT-6.1 Terra pricing into unit economics

Cost per userEstimate AI COGS per active customer →Agent costModel multi-step tasks and retries →Caching savingsModel repeated-context savings →