per 1M tokens
tencent/Hy4-preview
deepinfra/tencent/Hy4-preview
Hy4 preview is a 770B-parameter Mixture-of-Experts flagship model from the Tencent Hy Team, with 49B parameters activated per token and a 1M-token context window. It uses Gated DeepSeek Sparse Attention with IndexCache, and is post-trained for software engineering, office and data analysis, game development, and scientific research.
Price
per 1M tokens
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
No provider prices yet.
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$3.34 at list price for this workload
Cache
per 1M tokens
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.834/1M | $2.501/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-10-08 | token | $0.834 | $2.501 | Not published— |
| 2026-10-09 | token | $0.834 | $2.501 | Not published— |
| 2026-10-10 | token | $0.834 | $2.501 | Not published— |
| 2026-10-11 | token | $0.834 | $2.501 | Not published— |
| 2026-10-12 | token | $0.834 | $2.501 | Not published— |
| 2026-10-13 | token | $0.834 | $2.501 | Not published— |
| 2026-10-14 | token | $0.834 | $2.501 | Not published— |
| 2026-10-15 | token | $0.834 | $2.501 | Not published— |
| 2026-10-16 | token | $0.834 | $2.501 | Not published— |
| 2026-10-17 | token | $0.834 | $2.501 | Not published— |
| 2026-10-18 | token | $0.834 | $2.501 | Not published— |
| 2026-10-19 | token | $0.834 | $2.501 | Not published— |
| 2026-10-20 | token | $0.834 | $2.501 | Not published— |
| 2026-10-21 | token | $0.834 | $2.501 | Not published— |
| 2026-10-22 | token | $0.834 | $2.501 | Not published— |
| 2026-10-23 | token | $0.834 | $2.501 | Not published— |
| 2026-10-24 | token | $0.834 | $2.501 | Not published— |
| 2026-10-25 | token | $0.834 | $2.501 | Not published— |
| 2026-10-26 | token | $0.834 | $2.501 | Not published— |
| 2026-10-27 | token | $0.834 | $2.501 | Not published— |
| 2026-10-28 | token | $0.834 | $2.501 | Not published— |
| 2026-10-29 | token | $0.834 | $2.501 | Not published— |
| 2026-10-30 | token | $0.834 | $2.501 | Not published— |
Alternatives
- Hunyuan 4 Preview$0.834/1M · Compare
- Hy4 Preview$0.834/1M · Compare
- Tencent: Hy4 Preview$0.834/1M · Compare
- Tencent: Hy4 preview$0.834/1M · Compare
- Google: Gemini 3.8 Flash$0.825/1M · Compare
- Macaron V1 Venti$0.825/1M · Compare
Parameters (3)
chatprompt_cachereasoning
Call this model
OpenRouter id deepinfra/tencent/Hy4-preview. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepinfra/tencent/Hy4-preview","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "deepinfra/tencent/Hy4-preview",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "deepinfra/tencent/Hy4-preview", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())