Hy4-preview
- Model Introduction - A New Flagship Generation - Built for Productivity - Benchmark Appendix - Known Limitations - News - Model Links - Quickstart - Deployment - vLLM - SGLang - Finetuning - Quantization - License - Contact Us
Params
780.0 B
Context
1,048,576
Downloads 30d
18 K
Likes
514
Download history
tracking started — chart appears after 7 days of snapshots (6 recorded)18 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 1,560.0 GB | 1,833.5 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 1024K ctx | 1,560.0 GB | 16,691.7 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/hy4-preview
{
"hf_id": "tencent/Hy4-preview",
"params_b": 779.96,
"context_length": 1048576,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 18369,
"vram_estimates": [
{ "quant": "bf16", "gb": 1833.5 }
],
"updated_at": "2026-10-19T06:02:27Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.83
input / 1M
$2.50
output / 1M
$0.042
cached input / 1M
$3.34
1M in + 1M out
Price tiers
- Daily 16:00–00:00 UTC: input $0.75/M, output $2.25/M (0.9× base)
- Context window
- 1,048,576 tokens
- Max output
- 64,000 tokens
- Providers
- 5
- Cheapest provider
- Cohere · $0.83 / $2.50
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- — / — / —
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- HYV4ForCausalLM
- Parameters
- 780.0 B
- Tensor type
- BF16
- Context length
- 1,048,576
- Vocabulary
- 120,832
- Layers / heads
- 78 / 64
- Licence
- apache-2.0
- First seen on the Hub
- 2026-08-27
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model