Fast multilingual model with strong Arabic, image understanding and tool calling. Answers in seconds and handles a 262K context. The cheapest way to run vision work at scale: 8x more tokens per credit than premium models.
Qwen 3.5 9B delivers enterprise-grade performance optimized for high-throughput applications and complex reasoning tasks. With a massive 262,144-token context window, this model processes extensive documents and long conversations without losing coherence or accuracy. It excels in multilingual tasks, offering native-level Arabic understanding alongside English proficiency, ensuring precise communication across diverse languages. Built-in vision capabilities and reliable tool calling allow developers to build sophisticated agents that interpret images and execute external functions seamlessly within a single workflow. Benchmark tests confirm superior accuracy in language-specific tasks compared to similar parameter classes.
Efficiency is central to this architecture, operating at a 0.25x credit multiplier to provide eight times more tokens per credit than premium alternatives. This cost structure enables scalable vision workloads and high-volume text processing without compromising operational budgets. Integration is streamlined for immediate deployment, allowing API builders to establish connections and execute first calls within minutes of reading documentation. Developers can rely on consistent uptime and standardized API endpoints for frictionless integration. Whether optimizing research pipelines or production environments, Qwen 3.5 9B balances advanced reasoning with economical operation, ensuring robust support for demanding workflows while maintaining low latency responses for end users.
from openai import OpenAI
client = OpenAI(
base_url="https://llmapi.resayil.io/v1/",
api_key="YOUR_API_KEY"
)
response = client.chat.completions.create(
model="qwen3.5:9b",
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="qwen3.5:9b",
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: "qwen3.5:9b",
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": "qwen3.5:9b",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'