Hy3 preview pricing & benchmarks
Released Apr 22, 2026 · served by 1 provider · ranked #25 by intelligence in our index
What Hy3 preview is
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...
- Model ID:
tencent/hy3-preview - Modality: text->text
- Tool calling: supported · Structured output: not supported
- Weights:
tencent/Hy3-previewon Hugging Face
Providers and prices for Hy3 preview
The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| GMICloudcheapest | $0.063 | $0.210 | 262K | bf16 | 99.9% | — |
Cheaper models in the same class
Models scoring within 4 points of Hy3 preview on the Intelligence Index, but with a lower output price.
Compare Hy3 preview head-to-head
FAQ
How much does the Hy3 preview API cost?
$0.063 per 1M input tokens and $0.210 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.13.
Is Hy3 preview free?
No. It is a paid model starting at $0.063 per 1M input tokens, though some providers offer trial credits.
Which provider is cheapest for Hy3 preview?
GMICloud at $0.063 input / $0.210 output per 1M tokens (bf16 quantization).
Can I self-host Hy3 preview?
Yes — weights are published as tencent/Hy3-preview on Hugging Face, so you can run it on your own hardware.