All AI models · LLM benchmarks · Methodology

Tencent

Hy3

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Model facts

Context window
262K tokens
Maximum output
128K tokens
Cheapest paid input
$0.132 per 1M tokens
Cheapest paid output
$0.528 per 1M tokens
Open weights
yes
Providers
19

Capabilities and modalities

reasoning, tool calling, structured output, temperature control, open weights, text.

Local hardware estimate

At 4K context: Q4_K_M 173.9 GiB, Q8_0 313.0 GiB, F16 573.9 GiB working memory.

Parameters
298.8 billion
Architecture
hyv3
Model license
apache-2.0

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default42.258.8not measured92.5

Observed price history

  • 2026-08-24: $0.018 input / $0.072 output per 1M tokens
  • 2026-08-30: $0.083 input / $0.33 output per 1M tokens
  • 2026-08-31: $0.083 input / $0.33 output per 1M tokens
  • 2026-09-01: $0.083 input / $0.33 output per 1M tokens
  • 2026-09-02: $0.083 input / $0.33 output per 1M tokens
  • 2026-09-03: $0.083 input / $0.33 output per 1M tokens
  • 2026-09-04: $0.132 input / $0.528 output per 1M tokens

API providers