builds models · serves endpoints · 2026-08-14

Tencent

Models it builds

Model	Coding index	tok/s	$/M in	$/M out	$ / session	Cache
Tencent Hy3	58.8	66.5	$0.13	$0.53	$0.2951	87.0%

Models it serves

1 endpoints, cheapest first. This is the view the model-by-model tables cannot give you: what one provider actually offers, and at what precision.

Model	Quant	$/M in	$/M out	Context	Uptime 30m
Tencent Hy3	fp8	$0.13	$0.53	262,144	99.9%

Where to buy its models

Everyone serving these models, cheapest first, with the numeric precision each one runs. The lab is often not the cheapest place to buy its own model.

Model	Served by	Quant	$/M in	$/M out	Uptime 30m
Tencent Hy3	Baidu	fp8	$0.13	$0.51	99.9%
Tencent Hy3	GMICloud	bf16	$0.13	$0.53	99.2%
Tencent Hy3	Tencent	fp8	$0.13	$0.53	99.9%
Tencent Hy3	DeepInfra	fp8	$0.14	$0.58	96.5%
Tencent Hy3	Novita	unknown	$0.14	$0.58	100.0%
Tencent Hy3	AtlasCloud	fp8	$0.20	$0.80	99.8%

◆ Some links on this page are referral links: if you sign up through them this site may earn a commission, at no extra cost to you. Rankings, prices and measurements are taken from the sources listed under Method, and are not influenced by whether a provider has a referral programme.