Hy3
hy3Hy3 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:... Built by Tencent.
Prices updated
Input price
$0.13
per 1M tokens · Standard
Output price
$0.53
per 1M tokens · Standard
Input limit
262K
tokens
Output limit
128K
tokens
Input formats
Output formats
Hy3 price history
8 price records since 9/25/2026 · 6 changes
Hy3 cost calculator
$5.28/month
Standard pricing
Overview
What is Hy3?
Hy3 is a text & reasoning model from Tencent. 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:... Its 262K context window and $0.13 input price make it a candidate for cost-sensitive, high-throughput applications.
Benchmarks
Hy3 benchmarks & speed
How Hy3 scores on standardized evaluations, and where it lands among every model we track.
25.3
Intelligence Index
88tok/s
Output speed
1180
DesignArena Elo
Reasoning
GPQA Diamond
89.7%
Graduate-level scientific reasoning · top 28%
HLE
33.5%
Humanity's Last Exam · top 34%
Coding
SciCode
48.6%
Python for scientific computing · top 56%
Latency & design
- Time to first token
- 3.08s
- DesignArena win rate
- 41.1%
- Design battles judged
- 4,070
Independent scores from Artificial Analysis and DesignArena · updated 10/8/2026. Higher is better; ranks compare against every model we track with that score.
Rates
Hy3 pricing
Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.
Input · Standard
$0.13
Per 1M tokens
Cached input · Standard
$0.03
Per 1M tokens
Capabilities
Hy3 Tools
Tools available when using Hy3 through supported provider APIs.
Function calling
Supported
Structured outputs
Supported
JSON mode
Supported
Reasoning
Supported
Built-in web search
Not supported
Log probabilities
Not supported
Deterministic seed
Supported
Parallel tool calls
Not supported
Prompt caching
Supported
Strengths and limitations
Strengths
- Low input cost at $0.13 per million tokens suits high-volume workloads.
- 262K context supports large documents, repositories and extended conversations.
- Supports text & reasoning workloads in one model.
Limitations
- Generated tokens cost 4× more than input tokens, which matters for verbose responses.
- Large context capacity does not guarantee consistent retrieval across the entire prompt.
- Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.
Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.
Same provider