SambaNova has launched prompt caching for MiniMax M3 on SambaCloud, reducing input costs by 90% to $0.06 per million cached tokens and improving time to first token by 35% to 88% without code changes.
OpenAI Developers says applications can select reusable prompt prefixes with explicit cache breakpoints, change reasoning effort and tool availability while preserving cached context, and prewarm shared context so responses start sooner.
Higher default cache-hit rates let more GPT-6 input tokens receive cached-input discounts of up to 90%. OpenAI Developers says the change helps agents run faster and cost less.
A new Prompt Caching Dashboard on platform.openai.com tracks cache-hit rates. A diagnostics API identifies changes that prevented cache reuse and estimates how many tokens were affected.
OpenRouter says GPT-6 Sol and GPT-6 Luna use Astra's clearer, shorter, lower-jargon answers and OpenAI's improved prompt caching, with 90% off cached input reads.
Kimi.ai says Kimi K3 is available on Amazon Bedrock for coding, document analysis, and extended agent workflows, with Bedrock access, encryption, and auditing controls and support for explicit prompt caching.
