Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
Hy3 preview - Model - OpenSmartRoute
Modelv1.0.0
Hy3 preview
Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes
Reference model card from the OpenRouter listing - model tencent/hy3-preview. Prices are per million tokens as listed; ratings and installs below are from this marketplace.
Hy3 preview
Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...
Facts
Vendor
Tencent
Context window
262,144 tokens
Max output
235,929 tokens
Input price
$0.18 / 1M tokens
Output price
$0.60 / 1M tokens
Input
text
Output
text
Tool calling
yes
Structured outputs
no
Reasoning
yes
Open weights
tencent/Hy3-preview
Endpoint: https://openrouter.ai/api/v1 (OpenAI-compatible), model tencent/hy3-preview
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configure
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
# or pin it on the OpenAI-compatible endpoint: {"model": "model-tencent-hy3-preview", ...}
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
model-tencent-hy3-preview.ocm.jsonjson
{
"ocm": "1",
"id": "model-tencent-hy3-preview",
"kind": "llm",
"name": "Hy3 preview",
"description": "Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...",
"publisher": "Tencent",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"llm",
"tencent",
"openrouter",
"open-weights",
"reasoning",
"tool-calling",
"models"
],
"languages": [
"en"
],
"modalities": [
"text"
],
"supports_tools": true,
"supports_streaming": true,
"context_window": 262144
},
"quality_prior": 0.258,
"examples": [
"Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to..."
],
"primary": false,
"metadata": {
"source": {
"provider": "models",
"ref": "1776878150",
"url": "https://openrouter.ai/tencent/hy3-preview",
"key": "tencent/hy3-preview",
"catalogue": "https://openrouter.ai/api/v1"
},
"model": "tencent/hy3-preview",
"pricing": {
"input_usd_per_1m": 0.18,
"output_usd_per_1m": 0.6,
"cache_read_usd_per_1m": 0.06
},
"max_output_tokens": 235929,
"output_modalities": [
"text"
],
"hugging_face_id": "tencent/Hy3-preview",
"reasoning": true,
"created": 1776878150,
"benchmarks": {
"intelligence_index": 25.8,
"coding_index": 58.8,
"agentic_index": 25.6,
"hub_downloads": 71888,
"hub_downloads_total": 383997,
"hub_likes": 311,
"hub_trending": 2,
"osr_index": 35,
"osr_coverage": 0.4
}
},
"cost": {
"usd_per_1k_tokens": 0.00039
},
"endpoints": [
{
"protocol": "openai",
"url": "https://openrouter.ai/api/v1"
}
]
}
Fetch it by URL: GET /api/v1/registry/model-tencent-hy3-preview/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
