You can call the LLM API with the OpenAI SDK
— pricing
“unit price * 사용량” 만큼 보유 credit이 차감 됩니다
•
Input unit price(1,000 tokens): $0.0012
•
Output unit price(1,000 tokens): $0.0036
— pricing example
•
환율 1,446원 기준
•
Input unit proce(1,000 tokens) : 17.352 credit
•
Output unit price(1,000 tokens): 52.056 crdit
— API reference
base_url for SDK: https://api.hometip.net/ai-model/{model_id="qwen"}/v1
{MODEL_ID}: ["qwen"]
— base_url example
•
https://api.hometip.net/ai-model/qwen/v1/chat/completions
Available models: [ qwen2.5-72b-instruct, qwen2.5-vl-72b-instruct ]
— Text input
curl -X POST https://api.hometip.net/ai-model/qwen/v1/chat/completions \
-H "API-KEY: Bearer $SUBSCRIPTION_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen2.5-72b-instruct",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Who are you?"
}
]
}'
Bash
복사
—Schema
Messages array[Object]
you create prompts by providing an array of messages that contain instructions for the model. Each message can have a different role, which influences how the model might interpret the input.
role string
Instructions that request some output from the model. Similar to messages you'd type in Chat as an end user.
Description | Usage example |
user | Instructions that request some output from the model. Similar to messages you'd type in Chat as an end user. |
developer | Instructions to the model that are prioritized ahead of user messages, following chain of command. Previously called the system prompt. |
assistant | A message generated by the model, perhaps in a previous generation request (see the "Conversations" section below). |
— Image Input
curl -X POST https://api.hometip.net/ai-model/qwen/v1/chat/completions \
-H "API-KEY: Bearer $SUBSCRIPTION_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "qwen2.5-vl-72b-instruct",
"messages": [{
"role": "user",
"content":
[{"type": "text","text": "What is this"},
{"type": "image_url","image_url": {"url": "https://lkhtherapymi.com/wp-content/uploads/2016/09/h48-post-1.jpg"}}]
}]
}'
Bash
복사
