MODEL PROOF
Hy3 preview
BETTER VALUE OPTION
A stored alternative has an equal-or-higher measured score and an equal-or-lower price.
DeepSeek V4.1 Flash · Δ score 62.1 points · 59% lower measured price · $0.117 / 1M tokens (Price under confirmation since Nov 12, 2026)
GLM 5.3 Flash is a further stored option with these losses: 236K → 131K max output
- Independent LMArena score
- 1,401.3 ± 7.41 · 6,815 votes
- Context window
- 262.14K
- Maximum output
- 235.93K
- Input modalities
- text
- Output modalities
- text
- Published input price
- $0.180 / 1M tokens
- Published output price
- $0.600 / 1M tokens
- Pricing kind
- fixed
Inspect complete billing conditions and endpoint terms below.
Price from GMICloud: the cheapest offer that is serving, at standard delivery, with at least 90% of the reference context and at a declared precision that is not 4-bit (bf16), at its standard rate. The maker’s own precision is not known.
Every price dimension · USD per million tokens
| Input | $0.180/M |
|---|---|
| Output | $0.600/M |
| Cached input | $0.060/M |
| Cache write | Unknown/M |
| Cache write 1h | Unknown/M |
| Reasoning | Unknown/M |
Who sells it
The same weights, different shops. Cheapest is not like-for-like when serving precision differs.
1 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) |
|---|---|---|---|---|
| GMICloudgmicloud/bf16 Endpoint terms
| $0.180 | $0.600 | bf16 | 100.00% |
Independent scores
| LMArena Elo | 1401.3default |
|---|---|
| LMArena row | hunyuan-hy3-preview |
LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.
Capability
| Context window | 262K |
|---|---|
| Max output | 235K |
| Input modes | text |
| Tool use | yes |
| Reasoning | optional |
| Open weights | Unknown |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-11-12 |
| Quality data | verified |
Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...
Questions this page answers
What does Hy3 preview cost?
$0.180/M in, $0.600/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does Hy3 preview have an independent quality score?
Hy3 preview has an LMArena score in this catalogue.
What beats Hy3 preview?
DeepSeek V4.1 Flash has an equal-or-higher measured score and an equal-or-lower price.
Does this page use Artificial Analysis scores for Hy3 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.
MODEL MONUMENT