Qwen3 VL 235B A22B Instruct

Provider: Alibaba (Qwen) CN

Input price
$0.21
/ 1M tokens
Output price
$1.90
/ 1M tokens
Cache price
$0.10
/ 1M tokens (read)
Context
262K tokens
Max output 33K tokens

Overview

Alibaba's Qwen3 VL 235B A22B Instruct is a flagship multimodal model for vision-language tasks including VQA, document parsing, and chart extraction.

Strengths

  • 262,144 token context window
  • 32,768 token maximum output
  • Native vision and function-calling
  • Cached input rate of $0.1 per million tokens

Best use cases

  • Processing complex technical documents and charts
  • Multimodal analysis of images and video data
  • Structured data extraction via JSON mode

Pricing position

Input matches MiniMax M2.7 and DeepSeek V4.1 Flash at $0.21/1M tokens, but output is higher at $1.9/1M tokens.

Caveats

Carries no free tier and has a significantly higher output cost than smaller siblings like Qwen3 Next 80B.

Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
33K tokens
Knowledge cutoff
2025-03-31
Listed on OpenRouter
2025-09-23
Tracked since
2026-05-08
Last updated
2026-11-10

Features

Image inputFunction callingJSON output

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.12
1M (small app) 1 0.5 $1.16
10M (mid scale) 10 5 $11.60
100M (large) 100 50 $116.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Alibaba (Qwen)

Similar-priced models

Source: OpenRouter API (qwen/qwen3-vl-235b-a22b-instruct)