OpenAI adds 12-hour prompt caching to the API
OpenAI now lets developers choose a 12-hour cache lifetime in the Responses API for GPT-5.6 and later.
Models:gpt-5.6
On Zabio today
gpt-6.1-solLive. Call it by name with your Zabio key.Price and details
What changed
You can now choose a 12-hour prompt cache lifetime in the Responses API. For GPT-5.6 and later, cache writes cost 2.5x the ordinary input rate with the 12-hour lifetime, compared with 1.25x for the default 30-minute lifetime. Cache reads cost 0.1x the ordinary input rate on most of these models and 0.05x on GPT-6.1 Sol, regardless of the lifetime you select. The write rates are total rates, not surcharges on top of ordinary input.
Key details
- Set prompt_cache_options.ttl to 12h to choose the 12-hour lifetime.
- The default is 30m, and omitting the setting keeps that behavior.
- Cache reads cost 0.1x on most models and 0.05x on GPT-6.1 Sol, for either lifetime.
- OpenAI may keep entries longer than the minimum, and 12h sets no deletion deadline.
What it means for Zabio customers
The source recommends 12h for stable instructions or reference material reused across longer gaps, and the default 30m for conversations and agent steps that reuse context frequently.
Source
You can now choose 12-hour prompt caching in the API. 12-hour prompt caching keeps shared instructions, tools, and context cached longer to benefit from lower cached-input pricing, even when requests are hours apart.
Original announcement: OpenAI API changelog
How it compares
The models in this story next to models of the same class at a similar price, all available with one Zabio key.
| Model | Input, $/M | Output, $/M | Cached, $/M | Context window | 1,000 calls | Fixing code, hard |
|---|---|---|---|---|---|---|
gpt-6.1-solOpenAIIn this story | 2.00 | 10.00 | 0.10 | 400,000 | $9.00 | 82.1 |
gemini-4-argonGoogle | 2.00 | 10.00 | no data | 200,000 | $9.00 | 85.7 |
kimi-k3.1-proMoonshot AI | 2.00 | 10.00 | 0.20 | 1,048,576 | $9.00 | 67.8 |
qwen3.7-maxQwen | 2.50 | 7.50 | 0.50 | 1,000,000 | $8.75 | 77.3 |
Prices are the vendor list prices in USD per million tokens. "1,000 calls" is 1,000 requests of 2,000 input tokens and 500 output tokens each, without caching. Zabio bills the list price plus its service fee: see pricing.
Scores: percent correct for that kind of job, aggregated from public results by Epoch AI and LiveBench, read on 16 November 2026. Epoch AI: CC BY 4.0, LiveBench: Leaderboard results used with attribution; the 2.0 release states no terms of its own (read 2026-11-06); the first version's Mathematics, Language, IF results: Code Apache 2.0 and MIT; leaderboard results used with attribution
Source: OpenAI API changelog (2026-10-20)