Worked examples
The simulator's four example sessions on GPT-6.1 Terra with the 30 minute cache, priced turn by turn by the same cost model. Default on GPT-5.6 and later. This is a documented minimum; entries may last longer.
-
Coding agent
Tool calls and edits in quick succession, with a few longer pauses. 40 turns, 20K tokens of starting context, 3K in and 600 out per turn, 1.5 minutes apart, three long breaks of 8 minutes.
Open this in the simulator- With caching
- $0.50
- Without
- $3.85
- Saved
- $3.35 87%
- Pays for itself on turn 2
- Cache stays warm the whole way
-
Long chat
A person reading and typing, with one long break. 30 turns, 3K tokens of starting context, 150 in and 500 out per turn, 3 minutes apart, one long break of 45 minutes.
Open this in the simulator- With caching
- $0.13
- Without
- $0.45
- Saved
- $0.32 70%
- Pays for itself on turn 2
- Cache goes cold 1 time
-
Big document
One large document, questioned a dozen times. 12 turns, 150K tokens of starting context, 100 in and 700 out per turn, 7 minutes apart.
Open this in the simulator- With caching
- $0.33
- Without
- $1.90
- Saved
- $1.57 83%
- Pays for itself on turn 2
- Cache stays warm the whole way
-
Unattended loop
A script calling the model nonstop, the prompt growing every turn. 200 turns, 30K tokens of starting context, 1.5K in and 300 out per turn, 30 seconds apart.
Open this in the simulator- With caching
- $4.16
- Without
- $64.33
- Saved
- $60.17 94%
- Pays for itself on turn 2
- Cache stays warm the whole way
- Long-context prices from turn 135
The coding agent on each cache setting
The same 40-turn session, changing only the cache setting. Without caching it costs $3.85.
| Cache setting | With caching | Saved | Share saved | Pays off on turn |
|---|---|---|---|---|
| 30 minutes | $0.50 | $3.35 | 87% | 2 |
| 12 hours | $0.71 | $3.14 | 82% | 3 |
When caching pays for itself
For a prefix sent again and again inside the cache lifetime. The count does not depend on the prefix size, as long as it is above the minimum.
30 minutes
A write costs $1.25 per million tokens instead of $1.00, and each read within the lifetime costs $0.05 instead of $1.00.
A cached prefix pays for itself after 1 read within the lifetime.
Lifetime Default on GPT-5.6 and later. This is a documented minimum; entries may last longer.
12 hours
A write costs $2.50 per million tokens instead of $1.00, and each read within the lifetime costs $0.05 instead of $1.00.
A cached prefix pays for itself after 2 reads within the lifetime.
Lifetime Responses API only. This is a documented minimum; entries may last longer.
Caching rules for GPT-6.1 Terra
- Caching is automatic for prompts of at least 1,024 tokens. GPT-5.6 and later charge for writes: 1.25x the input price for at least 30 minutes, or 2.5x for at least 12 hours (Responses API only). OpenAI says these are total write rates, not surcharges on top of ordinary input.
- A read costs 0.05x the input price, and refreshes coverage to at least 30 minutes after the read.
- 30 minutes and 12 hours are minimums, and OpenAI may keep entries longer. The simulator uses the minimum.
- Short context is up to 272K input tokens. Above 272K, long-context prices apply: $2.00 input, $2.50 for a 30 minute write, $5.00 for a 12 hour write, $0.10 cached and $7.50 output. Assumed: the long-context rate applies to the whole request, cached and written tokens included. OpenAI's page states only the threshold.
Sources: OpenAI's pricing page, caching guide. See all prices and sources.
Similar models
Per million tokens, with the 40-turn coding agent on each model's default cache setting.
| Model | Input | Cache read | Output | Coding agent |
|---|---|---|---|---|
| GPT-6.1 Terra | $1.00 | $0.05 | $5.00 | $0.50 |
| GPT-5.4 mini | $0.75 | $0.075 | $4.50 | $0.71 |
| GPT-6.1 Sol | $2.00 | $0.10 | $10.00 | $1.00 |
| Claude Haiku 4.5 | $1.00 | $0.10 | $5.00 | $1.05 |
| Gemini 2.5 Pro | $1.25 | $0.125 | $10.00 | $0.89 best case* |
* Gemini implicit caching, best case.
Questions
What is the cached input price for GPT-6.1 Terra?
Input costs $1.00 per million tokens, $1.25 to write the 30 minute cache, $2.50 to write the 12 hour cache, $0.05 to read it and $5.00 for output.
Is prompt caching worth it for GPT-6.1 Terra?
In the 40-turn coding agent example, caching costs $0.50 against $3.85 without, a saving of $3.35 (87%). With the 30 minute cache, a cached prefix pays for itself after 1 read. It loses money only when the cache expires before it is read again.
How long does the GPT-6.1 Terra cache last?
30 minutes: Default on GPT-5.6 and later. This is a documented minimum; entries may last longer. 12 hours: Responses API only. This is a documented minimum; entries may last longer.
Does GPT-6.1 Terra have a minimum cacheable prompt length?
Yes. Prompts shorter than 1,024 tokens are not cached.
An estimate from published list prices, and your bill may differ. Token counts are what the example sets, not tokenized text. Not covered: batch and fast-mode prices, thinking tokens beyond the output shown, tool fees and regional uplifts.