News tagged "cost-optimization"

Claude Code 2.1.247 cost-optimize command and sub-agent model fallback chain fix for API gateway operators

Claude Code 2.1.247: The /claude-api cost-optimize Command Changes How Operators Audit API Spend

Claude Code 2.1.247 ships a built-in cost-profiling command that walks operators through caching, batch, token hygiene, and model-choice levers, and fixes a silent failure where sub-agents died on their first model call without activating the gateway fallback chain.

August 27, 2026via Claude Code Changelog

routing

Chinese AI Models Hit 46% of US Enterprise Token Traffic: What It Means for Your Routing Policy

Chinese models from DeepSeek, Z.ai, and Qwen now hold above 30% of US enterprise API token share every week on major routing platforms — peaking at 46%. Here is the routing and compliance framework operators need before moving production workloads.

July 13, 2026via CNBC

Three orbital bodies representing GPT-5.6 Sol, Terra, and Luna arranged in a clean editorial composition against a muted neutral background

openai

GPT-5.6 Sol, Terra, and Luna: Routing Policy for OpenAI's New Three-Tier Model Family

OpenAI previewed GPT-5.6 as three distinct model tiers — Sol, Terra, and Luna. For routing operators, the key shift is Terra: GPT-5.5-class performance at half the price. Here is how to update your routing policy before general availability lands.

June 29, 2026via OpenAI