OpenAIAnthropicGooglexAIPerplexity
← Back to all updatesPublished ·Anthropic• Minor
Claude Opus 4.8 lowers prompt caching’s minimum cacheable prompt length to 1,024 tokens versus Opus 4.7.
The read
Smaller prompts now qualify for caching, reducing the prompt size needed before repeated Opus 4.8 calls can cache.
The frame
For builders using prompt caching, the cache threshold moved down on Opus 4.8, changing which prompts are eligible.
Primary source
Anthropic →Keep reading
See what Nova3 builds →Related updates
- Jun 12, 2026Anthropic publicly documented stop_details on refusal responses, with category and explanation fields for routing.
- Jun 12, 2026Claude Opus 4.8 defaults the effort parameter to high across all surfaces.
- Jun 12, 2026Claude Opus 4.8 with adaptive thinking triggers reasoning only when a turn needs it.
This is the world we build in. It moves this fast. We move with it.
Bring us your project →