Hy-MT2-Lite

Set max_tokens on Hy-MT2-Lite to the longest response your task actually needs, not the 4,000-token ceiling. Keeping the cap tight reduces worst-case spend and shortens tail latency. Raise it only for tasks that demonstrably need longer output.

The current Hy-MT2-Lite listing publishes no cache-read rate, so cached-prefix billing is not part of its pricing. Treat repeated prefixes as fresh input when you size the workload, and confirm with the provider before designing for a cache saving.

The current model record does not publish a numeric rate limit for Hy-MT2-Lite. Confirm the quota for your plan in the console, then run a short load test at your expected concurrency to establish the effective ceiling before production.

Hy-MT2-Lite is billed per use and the record publishes no free-tier allowance. The current published rates are input $0.0440 per 1M tokens and output $0.1770 per 1M tokens. Trial credit or promotional quota is tied to your account rather than to the model, so check the console before planning around a free tier.

Hy-MT2-Lite returns up to 4,000 output tokens per request, within a 8,000-token context window. Cap the response with the max_tokens parameter so a single call cannot run past your budget.