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
Most third-party pricing tables are typed in once and quietly rot. This one is generated from a checked figure with the date and source recorded, and it is cross-checked on every deploy against the live model catalog Spendline uses to price real API traffic. If the two disagree, the site fails to build rather than publishing a stale number. 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?
The provider invoice is one number for the whole organization, so per-customer cost has to be attributed at the call. That means tagging every request with the customer, team, or agent it belongs to and recording the resolved cost against that tag in a ledger you can close monthly. Spendline does this by sitting in front of the API, which also lets a budget be enforced before the request is forwarded rather than reported after.
Know what this costs 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, or stop the one that is running away. Spendline sits in front of the API so every call is attributed and checked against a budget before it is forwarded.
Run the 5 minute assessment