Prompt Caching in the API
OpenAI is introducing automatic prompt caching for API users, providing discounts on input tokens that the model has recently processed. The feature reduces costs for repeated or overlapping prompt prefixes without requiring explicit developer configuration. This follows Anthropic's similar caching feature and reflects broader industry movement toward inference cost optimization.
Related guides (4)
Related events (8)
Understanding prompt injections: a frontier security challenge
OpenAI has published a blog post addressing prompt injection attacks as a key security challenge for AI systems. The post covers how these attacks work and outlines OpenAI's multi-pronged approach including research, model training improvements, and safeguard development. This signals OpenAI's formal positioning on agentic security threats as their models are increasingly deployed in tool-using and autonomous contexts.
Anthropic Publishes Quantitative Case Study on Prompt Engineering for Long-Context Recall
Anthropic shares a quantitative case study evaluating prompting techniques to improve Claude's recall over 75,000–90,000 token contexts. Two techniques are tested: extracting reference quotes before answering, and providing few-shot examples of correctly answered questions. The study uses Claude Instant 1.2 on a government document dataset constructed via a 'randomized collage' method, with multiple-choice Q&A pairs generated by Claude itself. Results show measurable recall improvements over a baseline prompt, with methodology and notebooks shared publicly.
OpenAI Announces Function Calling, Longer Context, and API Price Reductions
OpenAI introduced function calling capabilities to its API, enabling models to reliably output structured JSON for calling developer-defined functions. The update also includes longer context windows, more steerable models (gpt-3.5-turbo-16k and gpt-4 updates), and reduced pricing on several API tiers. These changes significantly expand the practical utility of OpenAI models for agentic and tool-use applications.
prompt-optimizer: Open-Source TypeScript Prompt Optimization Tool
prompt-optimizer is an open-source TypeScript tool designed to help users write better prompts and improve AI outputs. The repository has accumulated 29,603 total stars with 76 new stars today, indicating sustained community interest. It represents a category of tooling focused on prompt engineering automation and optimization.
OpenAI to Acquire Promptfoo
OpenAI announced the acquisition of Promptfoo, an AI security platform focused on identifying and remediating vulnerabilities in AI systems during development. The acquisition signals OpenAI's intent to deepen its enterprise security capabilities. Promptfoo has been widely used by developers to red-team and evaluate LLM applications for safety and reliability issues.
DeepSeek API Introduces Context Caching on Disk, Cutting Token Prices by ~90%
DeepSeek has launched a disk-based context caching service for its API, reducing cache-hit token pricing to $0.014 per million tokens versus $0.14 for cache misses—a 90% cost reduction. The system requires no code changes, runs automatically for prefix-matched inputs, and reduces first-token latency from ~13s to ~500ms on 128K prompts. DeepSeek attributes the feasibility of disk caching to the compact KV cache produced by its MLA (Multi-head Latent Attention) architecture in DeepSeek V2, which it claims makes it the first LLM API provider to deploy extensive disk caching at scale. The service supports up to 1 trillion tokens per day with no concurrency limits.
Designing AI agents to resist prompt injection
OpenAI published a blog post describing how ChatGPT's agent workflows are designed to resist prompt injection and social engineering attacks. The approach focuses on constraining risky actions and protecting sensitive data within agentic pipelines. This represents OpenAI's public articulation of defensive design principles for deployed AI agents.
OpenAI Introduces Enterprise-Grade Features for API Customers
OpenAI announced expanded enterprise capabilities for API customers, including enhanced security features and controls, updates to the Assistants API, and new cost management tools. The announcement targets enterprise adoption by addressing common organizational requirements around security, compliance, and budget oversight. No specific model capability changes are described.