Qwen2.5 VL 72B Instruct

Qwen2.5 VL 72B Instruct is the established 72B dense vision-language model from the 2.5 generation. Symmetric input/output pricing ($0.80/$0.80) makes it predictable for chunky multimodal workloads. Use it when you want a battle-tested VLM with broader real-world deployment history than the newer 3.x VL flagship, particularly for tasks where the 235B's extra capability would be overkill.

Quick start

Use any OpenAI-compatible client. Just change base_url and your key.

from openai import OpenAI

client = OpenAI(
    api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.thalam.ai/v1",
)

response = client.chat.completions.create(
    model="qwen/qwen2.5-vl-72b-instruct",
    messages=[
        {"role": "user", "content": "Hello from Thalam!"}
    ],
)

print(response.choices[0].message.content)