OpenAI pricing
GPT-5.6 Terra pricing
GPT-5.6 Terra bills per million tokens, metered separately for input and output. The current rates are below, along with the parts of the bill a per-token estimate leaves out.
GPT-5.6 Terra rates in full
All figures are USD per million tokens, taken from OpenAI’s own pricing documentation. The API model identifier is gpt-5.6-terra.
| Per million tokens | Standard, short context | Standard, long context |
|---|---|---|
| Input | $2 | $4 |
| Cached input read | $0.20 | $0.40 |
| Output | $12 | $18 |
What the rate table does not tell you
OpenAI prices this model in two bands. Long context input is double the short context rate and long context output is 50% higher, so the same workload can bill at two different rates depending on how much context each request carries.
Cached input is charged at 10% of the standard input rate in both bands.
A worked monthly example
Take 500,000 calls in a month at 3,000 input tokens and 400 output tokens each. That is 1.5 billion input tokens against 200 million output tokens, so input is 88% of the token volume.
| Line | Tokens | Rate | Cost |
|---|---|---|---|
| Input | 1,500M | $2 | $3,000 |
| Output | 200M | $12 | $2,400 |
| Total | 1,700M | $5,400 |
Output is 12% of the tokens and 44% of the bill. That inversion is why prompt trimming so often fails to move the invoice, and it is the single most common reason a forecast built on GPT-5.6 Terra comes in under the real number.
How this page stays current
The rate on this page was read off OpenAI’s published pricing and recorded with the date it was checked, September 16, 2026. The date changes only when someone checks again, not on each deploy. This model is also in the live model catalog Spendline uses to price API traffic, and our automated checks compare the two and fail if they disagree. At the last build the catalog agreed: $2 input and $12 output.
Frequently asked questions
How much does the GPT-5.6 Terra API cost?
GPT-5.6 Terra is billed per million tokens, metered separately for input and output. As of September 16, 2026 the rate is $2 per million input tokens and $12 per million output tokens, with cached input read at $0.20.
Why is my GPT-5.6 Terra bill higher than the per-token estimate?
Most estimates multiply expected tokens by the input rate and stop there. Output is priced at $12 against $2 for input, so responses usually dominate the bill even when prompts look larger. Reasoning tokens bill as output. Retries and agent fan-out pay full input cost for calls that produced nothing. And a cache that gets written but never read is pure overhead rather than a saving.
What is the cheapest way to run GPT-5.6 Terra?
Caching a stable prefix takes repeat input to $0.20, 10% of the standard rate, and pays for itself once the cached content is read more often than it is written. The larger lever is usually routing: sending the requests that do not need this tier to a cheaper model, and capping spend per customer before the call goes out.
How do I track GPT-5.6 Terra spend per customer or per feature?
Provider reports group usage by model, project or API key. Your application supplies the customer and workflow context needed to see cost per account. That means passing the customer, team or agent with each request from your server and recording the resolved cost against it. Spendline does this for supported requests routed through it, and checks configured budgets before forwarding them. Actual response cost can differ from the pre-call estimate.
See cost per customer, not just per token
A rate card tells you what a token costs. It does not tell you which customer, team or agent spent it. Spendline records attributed cost for supported requests routed through it and checks configured budgets before forwarding them.
Book a 30-minute call Explore a sample account