hy3
hy3Hy3 is the production version refined for real business scenarios. It uses a 295B total parameter, 21B active MoE architecture, natively supports a 256K context window, and provides no_think, think_low, and think_high reasoning modes to balance fast responses, complex reasoning, and usage cost. Compared with the Preview version, Hy3 is improved based on real feedback from Tencent Yuanbao, WorkBuddy, ima, Marvis, and other business scenarios, with stronger performance in Coding Agent workflows, long-context understanding, multi-turn context continuation, search Q&A, and complex task execution. It is more stable in reducing hallucinations, improving task completion, and supporting engineering usability, and is suitable for frontend tasks, cross-file code development, long-document analysis, office automation, and multi-step agent workflows.
- Published price
- From $0.105 / 1M tokensPrices from the model catalog
- Billing unit
- / 1M tokens
- Context / Max output
- 256K / 128K
- Listed routes
- 1
Provider routes
Published route pricing and available performance data. A dash means no data has been published.
| Provider | Pricing | Latency | Uptime | Supply | Route |
|---|---|---|---|---|---|
TencentLive | Input $0.105 / 1M tokens Output $0.418 · Cache $0.022 | 270ms | — | Verified |
- Input
- $0.105
- Output
- $0.418
- Cache read
- $0.022
- Cache write
- —
Prices are shown in each route’s billing unit. A dash means no price has been published. Source: the selected provider route in OpenAny's public model catalog. A price update timestamp is not supplied.
Playground
Try the selected route with a sample request before integrating it into your app.
Input
/v1/chat/completionsLoading live request metadata…
Result preview
Tencent · 270ms
Response example. Run to see the actual response.
{
"id": "chatcmpl_01JZ8X",
"object": "chat.completion",
"created": 1784012400,
"model": "hy3",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I help?"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 12,
"completion_tokens": 9,
"total_tokens": 21
},
"route": {
"mode": "auto",
"provider": "Tencent"
}
}Code examples
Use the selected model and provider route in your application.
curl 'https://api.openany.si/v1/chat/completions' \
-H "Authorization: Bearer $OPENANY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "hy3",
"route": {
"provider": "<provider-for-this-model>"
},
"route_mode": "balanced",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'Model API questions
How do I call hy3 through OpenAny?
Use model ID hy3 with an OpenAny key and the operation published in this model's API tab. The model API base is https://api.openany.si/v1. Confirm the protocol and request schema; model availability does not imply every OpenAI API operation is supported.
How is hy3 billed?
Compare the published rate and billing unit of the selected provider route. Input, output and cache token rates may differ. Image, audio and video models can use other units. Recorded usage determines the charge under that route's billing contract.
Are Community and Verified routes the same as an official publisher API?
No. Inspect the provider name and supply classification for the specific route. A marketplace listing or a supply label is not a claim of publisher endorsement, identical service or measured uptime. Different route prices may reflect different supply and conditions.
Where do these prices come from, and when were they updated?
Rates come from the provider routes in OpenAny's public model catalog, not an independent quote from the model publisher. The catalog does not supply a price update timestamp. A page or catalog snapshot date is not a price revision date. Compare supply, billing units, tiers and conditions; a lower listed rate alone does not establish equivalent service or explain the price difference.