MODEL PROOF
Hy4 preview
NO LMARENA GENERAL SCORE
No LMArena general score is attached to this listing.
Standard-window rate shown; discount 16:00–24:00 UTC every day: $0.751 in · $2.25 out. · Serving precision differs between offers.
- Independent LMArena score
- No LMArena general score
- Context window
- 1.05M
- Maximum output
- 64K
- Input modalities
- text
- Output modalities
- text
- Published input price
- $0.834 / 1M tokens
- Published output price
- $2.50 / 1M tokens
- Pricing kind
- fixed
Inspect complete billing conditions and endpoint terms below.
Price from Tencent: the cheapest offer that is serving, at standard delivery, with at least 90% of the reference context and at the maker’s precision or better, at its standard rate.
Every price dimension · USD per million tokens
| Input | $0.834/M |
|---|---|
| Output | $2.50/M |
| Cached input | $0.042/M |
| Cache write | Unknown/M |
| Cache write 1h | Unknown/M |
| Reasoning | Unknown/M |
Price varies by time of day. The headline is the standard rate, $0.834 in · $2.50 out. Discount window 16:00–24:00 UTC every day: $0.751 in · $2.25 out.The discount is 10% off input.The windows come from the tencent/fp8 endpoint in the upstream endpoints feed, not from the time this page was built.
Who sells it
The same weights, different shops. Cheapest is not like-for-like when serving precision differs.
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.834/M from Novita.
5 provider offers · rates, limits and conditions
Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test.
| Seller | Input | Output | Precision | Uptime (1d) |
|---|---|---|---|---|
| Novitanovita/fp8 Endpoint terms
| $0.834 | $2.50 | fp8 | 100.00% |
| SiliconFlowsiliconflow/fp8 Endpoint terms
| $0.834 | $2.50 | fp8 | 100.00% |
| Tencenttencent/fp8 Endpoint terms
| $0.834 | $2.50 | fp8 | 100.00% |
| DeepInfradeepinfra/fp4 Endpoint terms
| $0.834 | $2.50 | fp4 | 100.00% |
| Venicevenice/fp4 Endpoint terms
| $1.04 | $3.13 | fp4 | 100.00% |
Independent scores
No independent benchmark has measured this model. Unrated is not a score of zero.
Capability
| Context window | 1M |
|---|---|
| Max output | 64K |
| Input modes | text |
| Tool use | yes |
| Reasoning | optional |
| Open weights | Unknown |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-11-22 |
| Quality data | unrated |
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...
Questions this page answers
What does Hy4 preview cost?
$0.834/M in, $2.50/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does Hy4 preview have an independent quality score?
Hy4 preview has no LMArena general score in this catalogue. Unrated is not a score of zero.
What beats Hy4 preview?
Hy4 preview has no LMArena general score. Unrated is not a score of zero.
Does this page use Artificial Analysis scores for Hy4 preview?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.
Does a missing score mean Hy4 preview scored zero?
Unrated is not a score of zero.
Is the cheapest Hy4 preview endpoint the same product?
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.834/M from Novita.
MODEL MONUMENT