Alibaba Qwen: Qwen3 VL 235B A22B Instruct

Coming soonQuick Start

Qwen3 VL 235B A22B Instruct is Alibaba Qwen's open-weight multimodal model, released 2025-09, combining strong text generation with visual understanding across images and video. It handles document parsing, chart and table extraction, and multilingual OCR, while supporting agentic tool use and GUI automation. The model also turns sketches or mockups into code and assists with UI debugging, with text-only performance comparable to Qwen3 language models.

This model is not routed on MirAPI yet — prices shown are the official list prices. Create an account to get notified when it goes live.

Modalities
inTextinImageoutText
Price / 1M
$0.21 / $1.90
Context
262K
Knowledge cutoff
2025-03-31

Capabilities

VisionTool useLong contextPrompt cachingStructured output

Benchmarks

bar = score (0–100) · ▏ median

Scores from vendor reports and public leaderboards. No private evals.

GPQA Diamond
Science QA
70.9
#71
τ-bench (airline)
Agentic tool use
40.7
#88

Showcase

Three fixed prompts, identical for every chat model. Outputs are archived verbatim — copy the prompt to reproduce.

Task prompt · identical for all models
Build a single-file HTML page using three.js from a CDN: a low-poly planet with a tilted ring of ~200 orbiting particles, a soft key light plus rim light, slow auto-rotation, and drag-to-orbit controls. No build tools — one file only.
Archived output
Archive not published yet

Every model will run this exact prompt; the output lands here verbatim, with tokens and per-run cost.

Quick Start

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.mirapi.ai/v1",   # changed
    api_key=os.environ["MIRAPI_API_KEY"],   # changed
)

resp = client.chat.completions.create(
    model="qwen/qwen3-vl-235b-a22b-instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
Wire Qwen3 VL 235B A22B Instruct into your product

1M free tokens to start · no card · OpenAI-compatible, one base_url change

Start free