tokenstat
tokenstat
Tencent

Hy4 preview

tencent/Hy4-preview · rates as of · How this catalog is built · Benchmarks

A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.

Cheapest input
$0.67
$/MTok · models.dev
Cheapest output
$2
$/MTok
Context
1.0M
tokens
Sources
3
22 listings

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapesthy4-previewVancine$0.67$2$0.0341.0M
models.devtencent/hy4-previewOpenRouter$0.7506$2.25$0.03781.0M
models.devtencent/hy4-previewCommandCode$0.834$2.50$0.0421.0M
models.devtencent/Hy4-previewDeepInfra$0.834$2.50$0.0421.0M
models.devdeepinfra/tencent/Hy4-previewEden AI$0.834$2.50$0.0421.0M
models.devtencent/Hy4-previewHugging Face$0.834$2.50$01M
models.devtencent/hy4-previewKilo Gateway$0.834$2.50$0.0421.0M
models.devtencent/hy4-previewLLM Gateway$0.834$2.50$0.0421M
models.devtencent/hy4-previewNanoGPT$0.834$2.50$0.0421.0M
models.devtencent/hy4-previewNovita AI$0.834$2.50$0.0421M
models.devtencent/hy4-previewVercel AI Gateway$0.834$2.50$0.0421.0M
OpenRoutertencent/hy4-previewOpenRouter$0.834$2.50$0.0421.0M
models.devhy4-previewDevPass (LLM Gateway)$0.834$2.50$0.0421M
models.devhy4-previewOpenCode Go$0.834$2.50$0.0421.0M
models.devhy4-previewTencent Token Plan$0.834$2.50$0.0421.0M
models.devhy4-previewTencent TokenHub$0.834$2.50$0.0421.0M
models.devhy4-previewAIHubMix$0.845$2.54$0.04231.0M
LiteLLMhy4-previewN/A$0.845$2.54$0.0423N/A
models.devtencent/hy4-previewAI/ML API$0.8824$2.65$0.04441.0M
models.devtencent/hy4-previewCrossModel$0.96$2.88$0.0481.0M
models.devhy4-previewVenice AI$1.04$3.13$0.05251.0M
LiteLLMkyma/hy4-previewN/A$1.13$3.38$0.1126N/A

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Released: 2026-08-28Output limit: 64K tokensFamily: Hy

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

See what this model costs you

The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.