Hy3

Hy3 was released on 2026-07-06. Its catalog status is stable. Check the model page for deprecation notices before you build a long-lived integration on it.

Reasoning tokens are billed as output on Hy3, at $0.5280 per 1,000,000 token. They are generated before the visible answer and count toward both latency and spend, so a higher reasoning setting costs more even when the final answer is short.

Hy3 sits alongside llama-4-maverick-17b-128e-instruct-fp8, gemini-3.5-flash, qwen3.6-plus in the catalog. Compare them on the dimensions that change your bill and your users’ experience: task quality on your own prompts, latency at your concurrency, context and output limits, and cost per completed task rather than per token.

Before switching production traffic to Hy3, run a pilot on a representative slice of your traffic and check output quality, latency at peak concurrency, and cost per request. Verify the error and retry behaviour, and confirm the request limits you depend on match your plan.

Hy3 is a reasoning model. Reasoning effort can be tuned per request. Lower effort settings cut reasoning tokens and cost for routine work; reserve higher settings for problems that need deeper search. Measure quality at two or three settings before fixing one in production.