#api-costs

The latest AI and developer news about #api-costs, with the original source and a short summary.

Claude Code Prompt Cache: Triggers for Invalidation and TTL Configuration

Model switching and MCP server additions invalidate the cache, while file edits and subagents do not, with a default TTL of one hour for subscriptions.

·2026.11.01 11:00

OpenAI models now deployable on Google Cloud; new 12-hour prompt caching and Decisions API cut costs

New features include a Decisions API for efficient routing, zero-cost voice design, and GPT-Live-1.1 for faster real-time responses.

·2·2026.10.23 23:00

Benchmark Finds LLMs Read Cablese Records at Parity or Better Than Plain Text

A new benchmark, the Telegraph Test, demonstrates that LLMs can read compressed 'cablese' records with accuracy equal to or better than plaintext records, offering 25–49% token savings for machine-to-agent communication.

·2026.10.04 09:00

The Reversal of Token Costs

Even the same input can result in actual API costs differing by several times depending on the tokenizer.

·2·2026.04.17 05:00