Qwen3 VL 30B A3B Thinking

Provider: Alibaba (Qwen) CN

No longer listed on OpenRouter since 2026-11-15. The figures below are the last recorded values.
Input price
$0.29
/ 1M tokens
Output price
$1.00
/ 1M tokens
Context
262K tokens
Max output 236K tokens

Overview

Alibaba's Qwen3 VL 30B A3B Thinking is a reasoning and vision specialist for multimodal tasks and complex STEM reasoning.

Strengths

  • 262144 token context window
  • 235929 token max output
  • Supports vision and function-calling
  • Includes native thinking capability

Best use cases

  • Complex mathematical reasoning workflows
  • Visual document and image analysis
  • Structured JSON output generation

Pricing position

Input costs $0.29 and output costs $1.00 per million tokens, making it pricier than the $0.09 input and $0.30 output of Qwen3 30B A3B Instruct 2507.

Caveats

Has no free tier and features higher output pricing than Qwen3 30B siblings.

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
236K tokens
Knowledge cutoff
2025-03-31
Listed on OpenRouter
2025-10-06
Tracked since
2026-05-08
Last updated
2026-11-15

Features

Image inputFunction callingJSON outputReasoning

Price history

  • 2026-11-15 No longer listed

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.08
1M (small app) 1 0.5 $0.79
10M (mid scale) 10 5 $7.90
100M (large) 100 50 $79.00

※ 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-30b-a3b-thinking)