Skip to content
OpenSmartRoute
All vendors
Tencent

Vendor

Tencent models

7 models in the reference catalogue, vendor list prices per million tokens. 0 are routable on this deployment today.

Models

7

0 routable here

Cheapest (blended)

$0.08

Hy-MT2-1.8B

Median list price

$0.23

3:1 input to output per 1M tokens

Strongest

-

no published benchmarks

Every Tencent model

Newest first. Prices are the vendor's published rates per million tokens; click a model for the full specification.

ModelReleasedContextInput / 1MOutput / 1MIntelligenceCapabilities
Hy4 previewtencent/hy4-previewAug 28, 20261.0M$0.83$2.50-
reasoning tools
Hy-MT2-1.8Btencent/hy-mt2-1.8bAug 20, 20268K$0.04$0.18-
open weights
Hy-MT2-30B-A3Btencent/hy-mt2-30b-a3bAug 20, 20268K$0.07$0.29-
open weights
Hy-MT2-7Btencent/hy-mt2-7bAug 19, 20268K$0.07$0.29-
open weights
Hy3tencent/hy3Jul 6, 2026262K$0.13$0.53-
reasoning tools open weights
Hy3 previewtencent/hy3-previewApr 22, 2026262K$0.18$0.60-
reasoning tools open weights
Hunyuan A13B Instructtencent/hunyuan-a13b-instructJul 8, 2025131K$0.14$0.57-
reasoning open weights

Frequently asked

What is the cheapest Tencent model?
Hy-MT2-1.8B at $0.04 per 1M input tokens and $0.18 per 1M output tokens (vendor list price).
Which Tencent model has the largest context window?
Hy4 preview accepts 1.0M tokens of context.
How do I route to Tencent models with OpenSmartRoute?
Declare a target in targets.yaml with metadata.model set to the catalogue id (for example tencent/hy4-preview); the router scores it against every other target on cost, quality, latency and your policies for each request.

Route Tencent with everything else

OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a Tencent flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.