modelfax
Models/Tencent/Hy4 preview
TencentHy familyActive

Hy4 preview

A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.

JSONEmbed chartCompare
Context
1,048,576
Max output
65,536
Input / 1M
$0.67
Output / 1M
$2.00
Providers
11
01 Profile02 Capabilities03 Pricing04 History06 Related
01Profile

Profile

Released
2026-08-28
Last updated
2026-08-28
Knowledge cutoff
—
Weights
Open
02Capabilities

Capabilities

Input
text
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
No
Attachments
No
Cache read
—
Cache write
—
03Pricing

Pricing across 11 providers

Per 1M tokens, USD. Sorted by input price. First-party row highlighted.

ProviderProvider model idInputOutputCache readContext
vancinehy4-preview$0.67$2.00$0.031,024,000
kilotencent/hy4-preview$0.83$2.50$0.041,048,576
llmgatewayhy4-preview$0.83$2.50$0.041,000,000
llmgateway-providerstencent/hy4-preview$0.83$2.50$0.041,000,000
nano-gpttencent/hy4-preview$0.83$2.50$0.041,048,576
opencode-gohy4-preview$0.83$2.50$0.041,024,000
openroutertencent/hy4-preview$0.83$2.50$0.041,048,576
tencent-token-planhy4-preview$0.83$2.50$0.041,024,000
tencent-tokenhubhy4-preview$0.83$2.50$0.041,024,000
verceltencent/hy4-preview$0.83$2.50$0.041,024,000
crossmodeltencent/hy4-preview$0.96$2.88$0.051,048,576
04History

Change history

12+ recent events since 2026-08-28

2026-09-12Addedllmgatewayoffering→ new
2026-09-12Addedllmgateway-providersoffering→ new
2026-08-31ContextcrossmodelMax output1,048,576→ 65,536
2026-08-31Addedcrossmodeloffering→ new
2026-08-31Addedvancineoffering→ new
2026-08-28ContextkiloMax output64,000→ new
2026-08-28Addedkilooffering→ new
2026-08-28Addednano-gptoffering→ new
2026-08-28Addedopencode-gooffering→ new
2026-08-28ContextopenrouterMax output64,000→ new
2026-08-28Addedopenrouteroffering→ new
2026-08-28Addedtencent-token-planoffering→ new
as of 2026-09-16
About ·Corrections ·Contact ·Privacy ·EN / 中文 / 繁體
HomeModelsLabsProvidersToolsRankingsChangesNews