Hy3 preview
by Tencent · tencent/hy3-preview · #110 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:21 PM UTC · refreshed hourly
Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.18
per 1M tokens
Output
$0.60
per 1M tokens
Blended (3:1)
$0.285
3 input : 1 output
Cache read
$0.06
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Hy3 preview with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.285 | $0.019 | — |
| 50% | $0.24 | $0.013 | −32% |
| 90% | $0.204 | $0.00816 | −57% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.00027 | $0.27 |
| Document summary | 8,000 | 1,000 | $0.00204 | $2.04 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0066 | $6.60 |
| Long-context analysis | 150,000 | 5,000 | $0.03 | $30.00 |
Performance
Intelligence Index
22.7
AA composite quality
Coding Index
58.8
Math Index
—
Agentic Index
25.6
Output speed
0 tok/s
median
Time to first token
0s
median
Time to first answer
0s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 86.7% |
| Humanity's Last Exam | 27.8% |
| IFBench | 63.1% |
| AA-LCR (Long Context Reasoning) | 64.7% |
| Terminal-Bench Hard | 34.1% |
| τ²-Bench (Telecom) | 92.7% |
Specs
Context window
262K
tokens
Max output
236K
tokens
Input modalities
text
Tokenizer
Other