tokenstat
tokenstat
Tencent

Hy3 (Free)

tencent/Hy3 · rates as of · Benchmarks · AI plans · Calculator

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

Cheapest input
$0
$/MTok · models.dev
Cheapest output
$0
$/MTok
Context
262K
tokens
Sources
3
25 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. Showing free/$0 listings. Hide them.

SourceProviderInputOutputCache readContext
models.devcheapesthy3Kenari$0$0$0256K
models.devhy3Tencent Token Plan$0$0$0256K
models.devhy3Tencent TokenHub$0$0$0256K
models.devcheapesthy3:freeKenari$0$0$0256K
models.devhy3-freeOpenCode Zen$0$0$0190K
models.devtencent/hy3-freeOrcaRouter$0$0$0256K
models.devtencent/hy3NanoGPT$0.066$0.26$0.029262K
LiteLLMopenrouter/tencent/hy3N/A$0.0825$0.33$0.0206N/A
models.devtencent/hy3Kilo Gateway$0.132$0.528$0.033262K
models.devtencent/hy3LLM Gateway$0.132$0.528$0.033262K
OpenRoutertencent/hy3OpenRouter$0.132$0.528$0.033262K
models.devhy3DevPass (LLM Gateway)$0.132$0.528$0.033262K
models.devtencent/Hy3DeepInfra$0.14$0.58$0.035262K
models.devdeepinfra/tencent/Hy3Eden AI$0.14$0.58$0.035262K
models.devtencent/Hy3Hugging Face$0.14$0.58$0262K
models.devdeepinfra/hy3LLM Gateway$0.14$0.58$0.035262K
models.devtencent/hy3Vercel AI Gateway$0.14$0.58$0.035262K
models.devHy3Jalapeno Cloud$0.14$0.58$0203K
models.devhy3OpenCode Go$0.14$0.58$0.035256K
models.devhy3Requesty$0.14$0.58$0.035262K
LiteLLMtencent/Hy3N/A$0.14$0.58$0.035N/A
LiteLLMnovita/tencent/hy3N/A$0.14$0.58$0.035N/A
LiteLLMaihubmix/hy3N/A$0.1562$0.6248$0.0391N/A
models.devtencent/hy3CrossModel$0.16$0.64$0.04262K
models.devtencent/hy3OrcaRouter$0.18$0.59$0.059256K

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Released: 2026-07-06Family: 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.

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.