ModelPickr

Models / Tencent / Hy4 preview

Tencent · Hy

Hy4 preview

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

$0.83 in · $2.50 out

per 1M tokens · provider rate closest to the median. No first-party Tencent price was listed. The reference price is Deep Infra's rate, the provider closest to the median.

Provider input prices run from $0.67 to $1.15 per 1M tokens. Output prices run from $2.00 to $3.44.

Context
1,024,000
Max output
64,000
Cache read
$0.042
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Unknown
Vision
No
Open weights
Yes
License
—
Released
Aug 28, 2026
Updated in source
Aug 28, 2026
Knowledge
—
Providers
17

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
Vancine$0.67$2.00$0.034——
Kilo Gateway$0.75$2.25$0.038——
OpenRouter$0.75$2.25$0.038——
Deep Infrareference$0.83$2.50$0.042——
DevPass$0.83$2.50$0.042——
Eden AI$0.83$2.50$0.042——
Hugging Face$0.83$2.50———
LLM Gateway$0.83$2.50$0.042——
NanoGPT$0.83$2.50$0.042——
Novita AI$0.83$2.50$0.042——
OpenCode Go$0.83$2.50$0.042——
Tencent Token Plan$0.83$2.50$0.042——
Tencent TokenHub$0.83$2.50$0.042——
Vercel AI Gateway$0.83$2.50$0.042——
AIHubMix$0.85$2.54$0.042——
CrossModel$0.96$2.88$0.048$0.96—
AI/ML API$1.15$3.44$0.058——