DialModelsInfo typedef
The ids from a DIAL /openai/models response whose features.cache
flag is on (manual cache_breakpoint markers are honored for them),
plus the per-deployment reported limits (context window / max output —
from limits.max_total_tokens/max_prompt_tokens and
limits.max_completion_tokens).
Implementation
typedef DialModelsInfo = (
List<String> ids,
Set<String> cacheSupported,
Map<String, int> contextWindows,
Map<String, int> maxTokens,
);