Qwen3 VL 235B A22B Instruct

Qwen3 VL 235B A22B Instruct is the flagship vision-language model in the Qwen3 family. Mixture-of-experts architecture (235B total / 22B active) gives it frontier reasoning quality while keeping per-token cost in check. Native image understanding handles screenshots, charts, documents, and natural scenes; 131K context lets it work with long technical PDFs end-to-end. Best fit: document understanding, multimodal agents, OCR-adjacent workflows, and any task where you need vision + reasoning together.

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/qwen3-vl-235b-a22b-instruct",
    messages=[
        {"role": "user", "content": "Hello from Thalam!"}
    ],
)

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