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.
Qwen 2.5 7B Instruct delivers exceptional performance for high-volume workflows requiring speed and efficiency. Built on the Qwen family architecture, this model features a 32,768 token context window and native tool calling capabilities, making it ideal for classification, extraction, summarization, and chat applications. Developers can integrate immediately via our standard API endpoints, enabling you to complete your first API call within minutes without navigating complex documentation. The 7.6 billion parameter structure ensures low latency while maintaining robust reasoning capabilities suitable for production environments.
For teams scaling operations, this model offers the most cost-effective pathway to deployment. Operating at a 0.25x credit multiplier relative to base rates, you process eight times more tokens per credit compared to premium alternatives. This efficiency does not compromise linguistic versatility, as the model demonstrates strong proficiency in both English and Arabic tasks, satisfying research requirements for multilingual pipelines. Whether you are building cost-sensitive consumer applications or optimizing enterprise workflows, Qwen 2.5 7B Instruct provides the reliability and economic structure needed for large-scale implementation without requiring sales consultations for pricing transparency.
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!"}
]
}'