Skip to content

Hy3Disabled since Aug 28, 2026

Hosted probes for this catalog id fail with a bad request. The model is unlisted rather than advertised as a live hosted chat model.

Also accepted:tencent/Hy3

Tencent Hy3 — 295B/21B active MoE with native 256K context and three reasoning modes.

Providers
Capabilities
siliconflow
siliconflow
$0
$0
nousresearch
nousresearch
$0
$0
novita
novita
$0
$0
hoian
hoian
$0
$0
SiliconFlow
siliconflow-byok
$0
$0
Unavailable
OpenRouter
openrouter-byok
$0
$0
Unavailable
Nous Research
nousresearch-byok
$0
$0
Unavailable
NovitaAI
novita-byok
$0
$0
Unavailable
CommandCode
commandcode-byok
$0
$0
Unavailable
AIHubMix
aihubmix-byok
$0
$0
Unavailable
Usage analytics

Loading usage…

API & code
Uptime & Health
No uptime data yet

These providers haven't been health-probed for this model yet. The router still routes around upstreams that fail live requests — uptime fills in once probe history accrues.

Share cards
Hy3 share card
Hy3
siliconflow upstream share card
siliconflow upstream
SiliconFlow upstream share card
SiliconFlow upstream
OpenRouter upstream share card
OpenRouter upstream
Nous Research upstream share card
Nous Research upstream
nousresearch upstream share card
nousresearch upstream
Nous Research upstream share card
Nous Research upstream
Nous Research upstream share card
Nous Research upstream
novita upstream share card
novita upstream
NovitaAI upstream share card
NovitaAI upstream
hoian upstream share card
hoian upstream
CommandCode upstream share card
CommandCode upstream
AIHubMix upstream share card
AIHubMix upstream
Credits
Use your own key

Run Hy3 on your own key — your requests are billed by the provider. Pool callers pay AnyRouter credits.

No BYOK keys configured for this model yet.

Share a key with the pool to earn credits for every request it serves, covering your plan cost.

Text generation
Context length256,000 tokens
Max output204,800 tokens
ArchitectureTransformer
Categorytext
ReleasedJul 8, 2026
Modalities
Capabilities