AI model
tencent/hy3
Tencent: Hy3 is a 262,144-token model served on Composite at $0.103 per million tokens in and $0.413 per million tokens out. Ranked #77 of 179 models by traffic on Composite over the last 30 days, taking 0.06% of tokens and 0.06% of requests (this model and its routing variants). Measured on Composite, 99.0% of its last 100 requests on Composite succeeded, the typical first token arrives in 2731 ms, output runs at about 74.0 tokens per second.
Try in Playground| Model ID | tencent/hy3 |
|---|---|
| Provider | cv11 |
| Context window | 262,144 tokens |
| Accepts | text |
| Returns | text |
| Input price | $0.103 per million tokens |
| Output price | $0.413 per million tokens |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Thinking | Optional - see "Tencent: Hy3 (Reasoning)" in the catalog to turn it on by default |
| Moderated | No |
| Cost on a monthly plan | About 1.0 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 10 (base plus 9 routing variants) |
Make a Composite API key and type tencent/hy3 as the model name. JanitorAI takes the full URL https://composite.lucidity.sh/v1/chat/completions; SillyTavern, ChubAI, Agnai and RisuAI take https://composite.lucidity.sh/v1. It runs on credits, a plan, or your own provider key.
JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared
#77 of 179
0.06% of tokens and 0.06% of requests over 30 days, including routing variants.
99.0%
Across the last 100 requests Composite served for this model.
2731 ms
Median across the same sample.
74.0 tok/s
Median generation rate after the first token.
80.5%
Share of prompt tokens served from the provider's cache over 7 days.
The same model behind 9 alternative endpoints. Call the id directly to pin a route; the base id above picks for you.
| Route | Model ID | Provider | Price |
|---|---|---|---|
| Normal | tencent/hy3-normal |
cv11 | $0.103 per million tokens input · $0.413 per million tokens output |
| Normal + cheapThink | tencent/hy3-normal:cheapThink |
cv11 | $0.103 per million tokens input · $0.413 per million tokens output |
| Cheapest provider | tencent/hy3:cheapest-provider |
Tencent | $0.103 per million tokens input · $0.413 per million tokens output |
| Cheapest provider + cheapThink | tencent/hy3:cheapest-provider:cheapThink |
Tencent | $0.103 per million tokens input · $0.413 per million tokens output |
| cheapThink | tencent/hy3:cheapThink |
cv11 | $0.103 per million tokens input · $0.413 per million tokens output |
| Fast | tencent/hy3:fast |
Tencent | $0.103 per million tokens input · $0.413 per million tokens output |
| Fast + cheapThink | tencent/hy3:fast:cheapThink |
Tencent | $0.103 per million tokens input · $0.413 per million tokens output |
| Quality | tencent/hy3:quality |
GMICloud | $0.175 per million tokens input · $0.725 per million tokens output |
| Quality + cheapThink | tencent/hy3:quality:cheapThink |
GMICloud | $0.175 per million tokens input · $0.725 per million tokens output |
$0.103 per million tokens input · $0.413 per million tokens output
Credits pay the provider’s price plus 25%; cache hits cost less.
On a monthly plan, a typical call (8k tokens in, 1k out) uses about 1.0 plan credits, at the provider's own price.
cv11
This model is available on Composite alongside dozens of others from other labs, so it is easy to compare against similar options.
With a 262,144-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.
It is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
Supplied by cv11, not written by Composite.
Composite Anthropic Router · Composite Gemini Router · Composite GPT Router