OpenAIAnthropicGooglexAIPerplexity
← Back to all updatesPublished ·Anthropic• Minor
Anthropic added model capability fields to the Models API for model support discovery.
The read
Builders can query model limits and capabilities instead of hardcoding assumptions across Claude model calls.
The frame
This sits in model listing and lookup, giving builders one place to read supported token limits and capabilities.
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 lowers prompt caching’s minimum cacheable prompt length to 1,024 tokens versus Opus 4.7.
This is the world we build in. It moves this fast. We move with it.
Bring us your project →