Qwen3 VL 235B A22B Thinking
Alibaba · Multimodal · Released Sep 2025
A 235-billion-parameter multimodal vision-language model from Alibaba that processes text, images, and video with extended reasoning capabilities.
- Strengths
- Handles complex multimodal tasks and reasoning-heavy work across text, vision, and video inputs at the largest scale in Alibaba's vision-language lineup.
- Best for
- Dense reasoning tasks combining visual and textual analysis where the largest available capacity matters more than latency.
- Limitations
- The largest and slowest model in the Qwen3 VL series; smaller alternatives like the 30B Thinking tier offer faster inference for workloads that don't require the full 235B capacity.
Input / 1M
$0.4
Output / 1M
$4.00
Cached input / 1M
—
Context window
131K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in — out —
- 90d
- in decreased 0.0% out decreased 0.0%
- 1y
- in increased 53.8% out increased 53.8%
- Since launch
- in increased 53.8% out increased 53.8%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 7 Aug 2026 | $0.4 | $4.00 | — | Imported from OpenRouter | openrouter.ai |
| 6 Aug 2026 | $0.98 | $3.95 | — | Imported from OpenRouter | openrouter.ai |
| 5 Aug 2026 | $0.4 | $4.00 | — | Imported from OpenRouter | openrouter.ai |
| 3 Aug 2026 | $0.98 | $3.95 | — | Imported from OpenRouter | openrouter.ai |
| 29 Jul 2026 | $0.4 | $4.00 | — | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.26 | $2.60 | — | Imported from OpenRouter | openrouter.ai |