← All Models

Qwen: Qwen3 VL 235B A22B Thinking

🇨🇳 Qwen (Alibaba) · Qwen3 VL

Input Price $0.260 per million tokens NT$8.3
Output Price $2.60 per million tokens NT$83.2
Context Window 131K tokens Output limit: 33K
OpenRouter Route Price Please verify with official pricing pages
Use this model via OpenRouter →

Overview

Qwen: Qwen3 VL 235B A22B Thinking is a large language model API from Qwen (Alibaba), part of its Qwen3 VL model family. Priced at $0.260 per million input tokens and $2.60 per million output tokens, it occupies the mid-range, balancing capability against running cost. Output tokens cost about 10× as much as input, so prompt-heavy workloads run noticeably cheaper than generation-heavy ones. The 131K-token context window — around 197 pages of text — comfortably handles long documents, multi-file code, or extended conversations. Beyond plain text it also accepts Image input, so it can be applied to multimodal tasks rather than text alone. On Artificial Analysis's Intelligence Index it scores 21 (D grade), a useful proxy for its general reasoning strength relative to the other models tracked here. All prices on this page reflect OpenRouter's routed rates and are re-synced automatically every day; confirm against the provider's official pricing before committing to production.

Dimension Unit Price (USD) Price (TWD) Effective From
Input per 1M tokens $0.260 NT$8.3
Output per 1M tokens $2.60 NT$83.2

Provider
通義千問(阿里) (Qwen (Alibaba))
Model Family
Qwen3 VL
Version String
qwen/qwen3-vl-235b-a22b-thinking
Status
Active
Modality
Text, Image
Context Window
131,072 tokens
Output Limit
32,768 tokens

Index Metrics

Cross-domain capability indexes evaluated by Artificial Analysis — Artificial Analysis

Intelligence Index 21 D Measured: 2026-07-01

Benchmark Scores

Data source: Artificial Analysis

AA-LCR 58.7% C Measured: 2026-07-01
GPQA Diamond 77.2% A Measured: 2026-07-01
HLE 10.1% C Measured: 2026-07-01
IFBench 56.5% C Measured: 2026-07-01
MMMU Pro 68.7% B Measured: 2026-07-01
Non-Hallucination 17.5% Measured: 2026-07-01
Omniscience Accuracy 20.8% Measured: 2026-07-01
SciCode 39.9% B Measured: 2026-07-01
Tau2 54.1% Measured: 2026-07-01
TerminalBench 11.4% Measured: 2026-07-01

Performance Metrics

Real-world benchmarks, updated every 72 hours by Artificial Analysis — Artificial Analysis

First Token Latency 3.0s Measured: 2026-07-01
Output Speed 56 t/s Measured: 2026-07-01
Response Time 47.9s Measured: 2026-07-01

90-Day Price Trend

Input / Output price (USD per 1M tokens)

Past 90 days of records; every price change is shown here

Date Dimension Price (USD) Source
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter
Output $2.60 OpenRouter
Input $0.260 OpenRouter

Key Insights

Key data points from this page for quick reference and citation.

  • Qwen: Qwen3 VL 235B A22B Thinking Input price: $0.26/M tokens
  • Qwen: Qwen3 VL 235B A22B Thinking Output price: $2.6/M tokens
  • Context window: 131,072 tokens
  • Provider: Qwen (Alibaba)
  • Model family: Qwen3 VL
  • Modalities: Text, Image
  • Data source: OpenRouter, updated daily