Fast, low-cost model with tool calling for high-volume work — classification, extraction, summarising and chat. The cheapest way to run at scale: 8x more tokens per credit than premium models.
from openai import OpenAI
client = OpenAI(
base_url="https://llmapi.resayil.io/v1/",
api_key="YOUR_API_KEY"
)
response = client.chat.completions.create(
model="qwen2.5:7b-instruct-q4_K_M",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)import anthropic
client = anthropic.Anthropic(
base_url="https://llmapi.resayil.io/v1",
api_key="YOUR_API_KEY"
)
message = client.messages.create(
model="qwen2.5:7b-instruct-q4_K_M",
max_tokens=1024,
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(message.content[0].text)const response = await fetch(
"https://llmapi.resayil.io/v1/chat/completions",
{
method: "POST",
headers: {
"Content-Type": "application/json",
"Authorization": "Bearer YOUR_API_KEY"
},
body: JSON.stringify({
model: "qwen2.5:7b-instruct-q4_K_M",
messages: [
{ role: "user", content: "Hello!" }
]
})
}
);
const data = await response.json();
console.log(data.choices[0].message.content);curl https://llmapi.resayil.io/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "qwen2.5:7b-instruct-q4_K_M",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'