Hy4 previewOpen weights
Tencent · released 2026-08-28
No price from the maker itself is on record for Hy4 preview. The lowest of 19 providers is Vancine: $0.67 per 1M input tokens and $2 per 1M output tokens (as of 2026-11-12). Context window: 1.05M tokens, up to 64K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
VVancineLowesthy4-preview | $0.67 | $2 | $0.034 | Lowest | Official docs |
 CommandCodetencent/ | $0.834 | $2.501 | $0.042 | Official docs | |
 Deep Infratencent/ | $0.834 | $2.501 | $0.042 | Official docs | |
EEden AIdeepinfra/ | $0.834 | $2.501 | $0.042 | Official docs | |
EEden AItencent/ | $0.834 | $2.501 | $0.042 | Official docs | |
 Hugging Facetencent/ | $0.834 | $2.501 | — | Official docs | |
KKilo Gatewaytencent/ | $0.834 | $2.501 | $0.042 | Official docs | |
 DevPass (LLM Gateway)hy4-preview | $0.834 | $2.501 | $0.042 | Official docs | |
LLLM Gatewaytencent/ | $0.834 | $2.501 | $0.042 | Official docs | |
NNanoGPTtencent/ | $0.834 | $2.501 | $0.042 | Official docs | |
 Novita AItencent/ | $0.834 | $2.501 | $0.042 | Official docs | |
OOpenCode Gohy4-preview | $0.834 | $2.501 | $0.042 | Official docs |
8 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 OpenRoutertencent/ | $0.834 | $2.501 | $0.042 | Official docs | |
TTencent Token Planhy4-preview | $0.834 | $2.501 | $0.042 | Official docs | |
TTencent TokenHubhy4-preview | $0.834 | $2.501 | $0.042 | Official docs | |
 Vercel AI Gatewaytencent/ | $0.834 | $2.501 | $0.042 | Official docs | |
 AIHubMixhy4-preview | $0.845 | $2.535 | $0.04225 | Official docs | |
 AI/ML APItencent/ | $0.882372 | $2.646058 | $0.044436 | Official docs | |
CCrossModeltencent/ | $0.96 | $2.88 | $0.048 | Official docs | |
 Venice AIhy4-preview | $1.0425 | $3.12625 | $0.0525 | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
Price changes
| Date | Provider | Change |
|---|---|---|
| 2026-11-12 | Kilo Gateway | Input $0.7506 → $0.834 |
| 2026-11-12 | Kilo Gateway | Output $2.2509 → $2.501 |
| 2026-11-12 | Kilo Gateway | Cached $0.0378 → $0.042 |
| 2026-11-12 | NanoGPT | Input $0.7506 → $0.834 |
| 2026-11-12 | NanoGPT | Output $2.2509 → $2.501 |
| 2026-11-12 | NanoGPT | Cached $0.0378 → $0.042 |
| 2026-11-12 | OpenRouter | Input $0.7506 → $0.834 |
| 2026-11-12 | OpenRouter | Output $2.2509 → $2.501 |
| 2026-11-12 | OpenRouter | Cached $0.0378 → $0.042 |
| 2026-11-11 | Kilo Gateway | Input $0.834 → $0.7506 |
| 2026-11-11 | Kilo Gateway | Output $2.501 → $2.2509 |
| 2026-11-11 | Kilo Gateway | Cached $0.042 → $0.0378 |
| 2026-11-11 | NanoGPT | Input $0.834 → $0.7506 |
| 2026-11-11 | NanoGPT | Output $2.501 → $2.2509 |
| 2026-11-11 | NanoGPT | Cached $0.042 → $0.0378 |
| 2026-11-11 | OpenRouter | Input $0.834 → $0.7506 |
| 2026-11-11 | OpenRouter | Output $2.501 → $2.2509 |
| 2026-11-11 | OpenRouter | Cached $0.042 → $0.0378 |
About
A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.
Description from models.dev.
Specs
- Type
- Text
- Context
- 1.05M
- Max output
- 64K
- Input
- Text
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- —
- Open weights
- Yes
- Released
- 2026-08-28
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.