Door background frame
QWEN3-30B-A3B
600k+ Runs
QWEN3-30B-A3B visualization
QWEN3-30B-A3B
600k+ Runs
MoE with 30B active per pass; supports "thinking" and standard modes for high-quality reasoning, math, and code.

Qwen API Usage

POST /v1/chat/completions
import requests
import json

url = "https://api.akashml.com/v1/chat/completions"

payload = {
    "model": "Qwen/Qwen3-30B-A3B",
    "messages": [
        {
            "role": "user",
            "content": "Hello, how are you?"
        }
    ],
    "max_tokens": 150,
    "temperature": 0.7
}

headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer YOUR_API_KEY"
}

response = requests.post(url, json=payload, headers=headers)
print(response.json())
Pricing
Price (per 1M Tokens)
Model
Input
Output
QWEN3-30B-A3B
$0.07
$0.27
Model Details
Model Details
Provider
Alibaba
Type
Chat
Parameters
30B
Context Length
32k
Don't see the model you need?
Let us know, and we'll add it for you.
AkashML
X (Twitter)Discord
AI Inference Service
Akash Network
Built on Akash Network
Copyright 2025 © akashml.com