tencent Open weights Reasoning

Hy3 preview pricing & benchmarks

Released Apr 22, 2026 · served by 1 provider · ranked #25 by intelligence in our index

Input / 1M tokens$0.063
Output / 1M tokens$0.210
Context window262K
Cached input$0.021
Intelligence index41.2
Coding index58.8
Agentic index30.7
1M in + 300K out$0.13

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...

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.

ProviderInputOutputContext QuantUptime 24hThroughput
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.