DOS.AI
Newby DOS.AI
Ultra-efficient MoE model — 35B total, 3B active parameters. Fast inference at near-8B cost with 70B-class quality.
Run queries immediately, pay only for usage
Per 1M Tokens
About this model
DOS.AI is a Mixture-of-Experts model (35B total, 3B active per token) served on our own GPUs in Vietnam. It delivers 70B-class quality at 8B-class speed and cost, with strong multilingual, tool-calling, and coding performance. At $0.07 / $0.50 per million tokens it is roughly half the price of comparable providers, with full data residency in Vietnam.
Capabilities
Use Cases
- AI agents
- Customer support
- Content generation
- Code assistance
Model Details
- Provider
- DOS.AI
- Model ID
- dos-ai
- Parameters
- 35B MoE (3B active)
- Context Length
- 128K tokens
- Category
- chat
API Usage
Use the DOS API to integrate DOS.AIinto your applications. Our API is compatible with OpenAI's client libraries for easy migration.
Model ID
dos-aiPython
from dos import DOS
client = DOS()
response = client.chat.completions.create(
model="dos-ai",
messages=[
{"role": "user", "content": "Hello, how are you?"}
]
)
print(response.choices[0].message.content)cURL
curl https://api.dos.ai/v1/chat/completions \
-H "Authorization: Bearer $DOS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "dos-ai",
"messages": [
{"role": "user", "content": "Hello, how are you?"}
]
}'Node.js
import DOS from 'dos-ai';
const client = new DOS();
const response = await client.chat.completions.create({
model: "dos-ai",
messages: [
{ role: "user", content: "Hello, how are you?" }
]
});
console.log(response.choices[0].message.content);Related Models
DOS.AI Auto
Smart routing - automatically picks the best model for your request. Free for simple tasks, paid models for complex ones.
DeepSeek V4 Flash
1M-context fast tier replacing DeepSeek V3
GPT-5.4 Nano
Cheapest GPT-5.4-class model for simple high-volume tasks