hy3 API
Run tencent/hy3 through FastInfra's OpenAI-compatible API.
Pay per token, no subscription, routed to the cheapest available provider.
hy3 pricing
Billed per token used. Prices sync automatically from wholesale providers.
| Direction | Price per 1M tokens |
|---|---|
| Input | $0.14 |
| Output | $0.55 |
Served by 3 providers
Requests route to OpenRouter by default (cheapest).
Pin a specific provider with the :provider suffix.
| Provider | Upstream model ID |
|---|---|
| openrouter | tencent/hy3 |
| deepinfra | tencent/Hy3 |
| siliconflow | tencent/Hy3 |
Call hy3 in 30 seconds
Works with any OpenAI SDK — change the base URL and API key only.
Python
from openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.fastinfra.ai/v1")
response = client.chat.completions.create(
model="tencent/hy3",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)curl
curl https://api.fastinfra.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tencent/hy3",
"messages": [{"role": "user", "content": "Hello!"}]
}'hy3 — common questions
How much does the tencent/hy3 API cost?
On FastInfra, tencent/hy3 costs $0.1386/1M input, $0.5544/1M output tokens. Billing is per token used, with no subscription.
Is tencent/hy3 compatible with the OpenAI SDK?
Yes. FastInfra exposes tencent/hy3 through an OpenAI-compatible endpoint at https://api.fastinfra.ai/v1 — point any OpenAI SDK at that base URL with a FastInfra API key and keep your existing code.
Which providers serve tencent/hy3?
tencent/hy3 is available from 3 provider(s): openrouter, deepinfra, siliconflow. Requests route to OpenRouter by default (cheapest); append ":provider" to the model ID to pin one.
Related models
Compare side by side: hy3 vs All Minilm · hy3 vs Gemma2:2b · hy3 vs Gemma3:1b