In addition to the standard 5-minute prompt caching TTL, we now offer an extended 1-hour TTL. This reduces costs by up to 90% and reduces latency by up to 85% for long prompts, making extended agent workflows more practical.
LLMS
-
Anthropic Launches Four New API Capabilities for AI Agents
By
–
Today, we're announcing four new capabilities on the Anthropic API to help developers build more powerful AI agents.
— Anthropic (@AnthropicAI) 22 mai 2025
A code execution tool, MCP connector, Files API, and extended prompt caching: pic.twitter.com/Ie9EcOrf0MToday, we're announcing four new capabilities on the Anthropic API to help developers build more powerful AI agents. A code execution tool, MCP connector, Files API, and extended prompt caching:
-
Four New Features Now Available in Public Beta on Anthropic API
By
–
All four new features are available today in public beta on the Anthropic API. Read more in our docs:
-
Extended Prompt Caching TTL Reduces Costs and Latency
By
–
In addition to the standard 5-minute prompt caching TTL, we now offer an extended 1-hour TTL. This reduces costs by up to 90% and reduces latency by up to 85% for long prompts, making extended agent workflows more practical.
-
Files API: Upload Documents Once, Reference Across Conversations
By
–
The Files API lets you upload documents once and reference them repeatedly across conversations. This simplifies workflows for devs working with knowledge bases, documentation, or datasets.
-
Claude API Now Supports Direct MCP Server Connection
By
–
You can now connect Claude to MCP servers directly in the API. Just add a server URL to your API request and Claude handles tool discovery, execution, and error management automatically.
-
Claude’s Code Execution Tool Enhances Data Analysis and Math Tasks
By
–
The code execution tool allows Claude to run python code that it generates in a secure sandboxed container.
— Alex Albert (@alexalbert__) 22 mai 2025
This is a big boost for any tasks involving data analysis or math. pic.twitter.com/hXRmBvEhFqThe code execution tool allows Claude to run python code that it generates in a secure sandboxed container. This is a big boost for any tasks involving data analysis or math.
-
Anthropic API Gets Four Major New Features
By
–
We’ve added four new features to the Anthropic API today:
– Code execution tool
– MCP connector
– Files API
– Extended prompt caching Let’s dive in: -
Memory RAG and Mini-Agents: Reducing LLM Hallucinations
By
–
Interested in best practices for memory RAG and memory tuning to reduce LLM hallucinations? @LaminiAI CEO and co‑founder @realSharonZhou will join us at #DataAISummit to explore building compound AI systems by combining SLMs with highly accurate mini‑agents — don’t miss it:
-
AI Talks SF Event Features Top AI Research Lab Speakers
By
–
"AI Talks" is happening tomorrow in SF! we'll have an amazing list of speakers from top research labs like @FAL
, @LumaLabsAI
, @leonardoai , or @bfl_ml
. join here: https://
partiful.com/e/w1iypWDG76D2
9m6ZWsK1
…