模型详情
hy3
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings. Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.
模型规格
- 上下文长度
- –
- 最大输出
- –
- 输入/输出模态
- –
- 发布日期
- 2026-07
02
API 端点
单一 MixRoute 网关,OpenAI 兼容
-
OpenAI-compatible
/v1/chat/completionsPOST
03
价格
固定费率,单位:/1M Tokens
输入
$0.1320 /1M Tokens
补全
$0.5280 /1M Tokens
缓存读取
$0.0330 /1M Tokens
08
Token 成本估算
基于本页价格的实时估算,非实际账单
同一前缀被重复读取的输入占比,最高 100%
单一端点,可验证的决策
使用相同的请求格式测试此模型和备用路由
从真实工作负载开始,再由质量、总成本和故障条件决定是否接入生产流量。