Automatic Prompt Caching for API Cost and Latency Savings
Reduce API costs and latency by automatically reusing recently seen input tokens with Prompt Caching.
Prompt Caching
50% discount and faster processing times
Starting today, Prompt Caching is automatically applied on the latest versions of GPT‑4o, GPT‑4o mini, o1‑preview and o1‑mini, as well as fine-tuned versions of those models. API calls to supported models will automatically benefit from Prompt Caching on prompts longer than 1,024 tokens. The API caches the longest prefix of a prompt that has been previously computed, starting at 1,024 tokens and increasing in 128-token increments. If you reuse prompts with common prefixes, we will automatically apply the Prompt Caching discount without requiring you to make any changes to your API integration.
OpenAI's Prompt Caching automatically discounts API calls that reuse recently seen input tokens. This feature offers a 50% cost reduction and faster processing for prompts longer than 1,024 tokens on supported GPT-4o and other models, requiring no changes to existing API integrations.
By reusing recently seen input tokens, developers can get a 50% discount and faster prompt processing times.
- Prompt Caching in the API ↗OpenAI · OpenAI News · Oct 1, 2024 · paraphrased
First seen on Subvolts Oct 1, 2024. Updated Sep 11, 2026. Spotted a problem? Tell us.
- Prompt Caching in the APIOpenAI · OpenAI News · Oct 1, 2024
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- ToolOpenAI Prompt Caching for API Cost and LatencyA feature that automatically discounts and speeds up API calls by reusing recently seen input tokens. · 5 min
- Model pickGPT-6 model choice for reasoning and task typeMatch GPT-6 model and reasoning effort to workload for balance of capability, cost, and latency. · 5 min
- Cost tipGPT-6.1 Sol offers lower token costs than GPT-6 AstraUse GPT-6.1 Sol for agentic coding, computer use, and professional work to get similar intelligence to GPT-6 Astra at a lower price. · 5 min
- Cost tipReduce GPT-6 Luna costs with cached tokensUse cached input tokens to lower costs for high-volume tasks. · 5 min
- Cost tipManage GPT-6 Luna costs for large token promptsBe aware of increased pricing for prompts exceeding 272K input tokens. · 5 min
- ChecklistEvaluate AI model performance and costChecklist for comparing AI models on key metrics like latency, tokens, quality, and cost. · 15 min
Questions people ask
- Which AI tools does this work with?
- The sources used it with ChatGPT.
- Where did this come from?
- OpenAI (OpenAI News). Subvolts collected, normalized and credited it; the link above opens the original.