- Context window
- 1,000,000
- You save
- 95%
About HY4 Preview API pricing
HY4 Preview is available through the zcloud gateway behind one API key, alongside every other model in the catalog. HY4 Preview API pricing is pay-as-you-go: $0.0417 per 1M input tokens and $0.12505 per 1M output tokens — no subscription, no monthly minimum, and the same OpenAI-compatible endpoint your tools already use.
Against the official API — $0.834 input and $2.501 output per 1M tokens — zcloud runs about 95% cheaper, so sustained workloads cost a fraction of list price. Every request is metered per token and settled in real time, and live rates stay visible on the pricing page. The model provides a 1,000,000 token context window, so long documents, large codebases and extended agent sessions fit in a single request.
For predictable spend, prepaid Token Plans for HY4 Preview start at $1 and are consumed first; PAYG covers anything beyond the plan. HY4 Preview runs behind the same OpenAI-compatible and Anthropic-compatible endpoints as the rest of the catalog, so existing tooling keeps working after a one-line base-URL change — a practical fit for chat products, coding agents and batch jobs that need frontier quality without official-API prices.
Official price
PAYG rates · per 1M tokens
input
95%- $0.834
- Official price
- $0.0417
- zrouter price
output
95%- $2.501
- Official price
- $0.12505
- zrouter price
Token Plan tiers
Token Plans are tied to one model. Your plan balance is used first, then PAYG covers the remainder.
45,600,000 tokens
91,200,000 tokens
228,000,000 tokens
456,000,000 tokens