tokenstat
tokenstat
Aihubmix

Hy3 Preview

aihubmix/hy3-preview · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$0.063
$/MTok · OpenRouter
Cheapest output
$0.21
$/MTok
Context
262K
tokens
Offers
7
2 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (1 omitted). Show free/$0 offers.

SourceProviderInputOutputCache readContext
OpenRoutercheapesttencent/hy3-previewOpenRouter$0.063$0.21$0.021262K
models.devtencent/hy3-previewNanoGPT$0.066$0.26$0.029262K
models.devtencent/Hy3-previewSiliconFlow$0.066$0.26$0.029262K
models.devhy3-previewAIHubMix$0.17$0.5667$0.051256K
models.devtencent/hy3-previewZenMux$0.172$0.572$0.058256K
models.devtencent/hy3-previewKilo Gateway$0.18$0.6$0.06262K
models.devtencent/hy3-previewCrossModel$0.19$0.63$0.063262K

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Released: 2026-04-20Family: Hy

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.

Sources: Arena AI, Artificial Analysis. See /benchmarks.

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash