OpenAI Prompt Caching for API Cost and Latency
A feature that automatically discounts and speeds up API calls by reusing recently seen input tokens.
Prompt Caching
For
Reducing costs and latency for developers using the OpenAI API by reusing recently seen input tokens.
Pricing
50% discount on reused tokens
Url
https://openai.com/index/api-prompt-caching
What it does and when to use it
Prompt Caching is an OpenAI API feature that automatically provides a 50% discount and reduces latency by reusing previously processed input tokens for supported models.
Why it works
By reusing recently seen input tokens, developers can get a 50% discount and faster prompt processing times.
Sources and credit
- 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.
Where it shows up
- Prompt Caching in the APIOpenAI · OpenAI News · Oct 1, 2024
Terms used
Related in the PlaybookPlaybook →
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- Cost tipAutomatic Prompt Caching for API Cost and Latency SavingsReduce API costs and latency by automatically reusing recently seen input tokens with Prompt Caching. · 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
- 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
- ChecklistEvaluate AI model performance and costChecklist for comparing AI models on key metrics like latency, tokens, quality, and cost. · 15 min
- Cost tipReduce GPT-6 Luna costs with cached tokensUse cached input tokens to lower costs for high-volume tasks. · 5 min
- Cost tipFree training tokens for GPT-4o and GPT-4o miniGet free training tokens for GPT-4o and GPT-4o mini through September 23. · 5 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.