List prices
| Input | Short context | $2 / 1M tok |
| Cached input | Short context | $0.2 / 1M tok |
| Cache writes | Short context | $2.5 / 1M tok |
| Output | Short context | $12 / 1M tok |
| Input | Long context | $4 / 1M tok |
| Cached input | Long context | $0.4 / 1M tok |
| Cache writes | Long context | $5 / 1M tok |
| Output | Long context | $18 / 1M tok |
Estimate your monthly cost
Based on GPT-5.6 Terra's current list prices. You pay your provider directly - Vevee meters this usage against your own plans.
Repeated prompts can be cheaper: cached input is $0.200 / 1M tokens.
Frequently asked questions
How much does GPT-5.6 Terra cost?
GPT-5.6 Terra costs $2 per 1 million input tokens and $12 per 1 million output tokens, with cached input at $0.2 per 1 million tokens. These are OpenAI's list rates for the Short context tier.
How much does a typical GPT-5.6 Terra request cost?
A request with 1,500 input tokens and 500 output tokens costs about $0.0090. At 1,000 such requests a month that is roughly $9.00.
How many GPT-5.6 Terra tokens do I get for $10?
$10 buys roughly 5.0 million input tokens or 0.8 million output tokens at list price.
How do I track GPT-5.6 Terra costs per end user?
Use a metering layer. With Vevee you call track() or reserve()/commit() around each GPT-5.6 Terra request with the end user's ID, define plan limits in the dashboard, and Vevee enforces them and shows per-user usage and cost - no backend to build.
Track GPT-5.6 Terra spend per user
Knowing the list price is half the problem - the other half is knowing which of your users consume it and stopping the ones who blow past their plan. Vevee meters every GPT-5.6 Terra call per end user, enforces your plan limits, and shows you per-user cost. Free tier, no card.