per 1M tokens
Tencent: Hy3 preview
tencent/hy3-preview
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...
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.
| Provider | Tag | Quant | Input | Output | Context | Uptime | Status | Source |
|---|---|---|---|---|---|---|---|---|
| GMICloud | gmicloud/bf16 | bf16 | $0.18/1M | $0.6/1M | 262K | 100% | Live | openrouter-endpoints |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$0.78 at list price for this workload
Cache
per 1M tokens
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.18/1M | $0.6/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-09-15 | token | $0.18 | $0.6 | Not published— |
| 2026-09-16 | token | $0.18 | $0.6 | Not published— |
| 2026-09-17 | token | $0.18 | $0.6 | Not published— |
| 2026-09-18 | token | $0.18 | $0.6 | Not published— |
| 2026-09-19 | token | $0.18 | $0.6 | Not published— |
| 2026-09-20 | token | $0.18 | $0.6 | Not published— |
| 2026-09-21 | token | $0.18 | $0.6 | Not published— |
| 2026-09-22 | token | $0.18 | $0.6 | Not published— |
| 2026-09-23 | token | $0.18 | $0.6 | Not published— |
| 2026-09-24 | token | $0.18 | $0.6 | Not published— |
| 2026-09-25 | token | $0.18 | $0.6 | Not published— |
| 2026-09-26 | token | $0.18 | $0.6 | Not published— |
| 2026-09-27 | token | $0.18 | $0.6 | Not published— |
| 2026-09-28 | token | $0.18 | $0.6 | Not published— |
| 2026-09-29 | token | $0.18 | $0.6 | Not published— |
| 2026-09-30 | token | $0.18 | $0.6 | Not published— |
| 2026-10-01 | token | $0.18 | $0.6 | Not published— |
| 2026-10-02 | token | $0.18 | $0.6 | Not published— |
| 2026-10-03 | token | $0.18 | $0.6 | Not published— |
| 2026-10-04 | token | $0.18 | $0.6 | Not published— |
| 2026-10-05 | token | $0.18 | $0.6 | Not published— |
| 2026-10-06 | token | $0.18 | $0.6 | Not published— |
| 2026-10-07 | token | $0.18 | $0.6 | Not published— |
| 2026-10-08 | token | $0.18 | $0.6 | Not published— |
| 2026-10-09 | token | $0.18 | $0.6 | Not published— |
| 2026-10-10 | token | $0.18 | $0.6 | Not published— |
| 2026-10-11 | token | $0.18 | $0.6 | Not published— |
| 2026-10-12 | token | $0.18 | $0.6 | Not published— |
| 2026-10-13 | token | $0.18 | $0.6 | Not published— |
| 2026-10-14 | token | $0.18 | $0.6 | Not published— |
| 2026-10-15 | token | $0.18 | $0.6 | Not published— |
| 2026-10-16 | token | $0.18 | $0.6 | Not published— |
| 2026-10-17 | token | $0.18 | $0.6 | Not published— |
| 2026-10-18 | token | $0.18 | $0.6 | Not published— |
| 2026-10-19 | token | $0.18 | $0.6 | Not published— |
| 2026-10-20 | token | $0.18 | $0.6 | Not published— |
| 2026-10-21 | token | $0.18 | $0.6 | Not published— |
| 2026-10-22 | token | $0.18 | $0.6 | Not published— |
| 2026-10-23 | token | $0.18 | $0.6 | Not published— |
| 2026-10-24 | token | $0.18 | $0.6 | Not published— |
| 2026-10-25 | token | $0.18 | $0.6 | Not published— |
| 2026-10-26 | token | $0.18 | $0.6 | Not published— |
| 2026-10-27 | token | $0.18 | $0.6 | Not published— |
| 2026-10-28 | token | $0.18 | $0.6 | Not published— |
| 2026-10-29 | token | $0.18 | $0.6 | Not published— |
| 2026-10-30 | token | $0.18 | $0.6 | Not published— |
Alternatives
- DeepSeek R1 Distill Qwen 1.5B$0.18/1M · Compare
- Llama 4 Scout Instruct$0.18/1M · Compare
- Llama 4 Scout Instruct (17Bx16E)$0.18/1M · Compare
- Meta Llama 3.1 8B Instruct Turbo$0.18/1M · Compare
- meta-llama/Llama-Guard-4-12B$0.18/1M · Compare
- Meta: Llama Guard 4 12B$0.18/1M · Compare
Parameters (9)
include_reasoningmax_tokensreasoningreasoning_effortseedtemperaturetool_choicetoolstop_p
Call this model
OpenRouter id tencent/hy3-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":"tencent/hy3-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: "tencent/hy3-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": "tencent/hy3-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())