Qwen2.5-VL-32B-Instruct
Qwen · Mid-tier
Rates per million tokens
Input
$0.20
Output
$0.60
Cache read
$0.02
A new account opens on 16% off these rates, so input runs at $0.168 per million tokens.
Model id
Pass this as model in any OpenAI-compatible request.
Call it
from openai import OpenAI
client = OpenAI(
base_url="https://api.routedly.ai/v1",
api_key="sk-sr-cli-..."
)
response = client.chat.completions.create(
model="qwen-qwen2-5-vl-32b-instruct",
messages=[{"role": "user", "content": "Say hello"}],
)
print(response.choices[0].message.content)Start calling Qwen2.5-VL-32B-Instruct
One key works across every model in the catalog. No per-provider accounts.