All modelsCalculate what your real prompts cost on Qwen3 VL 235B A22B Thinking
Qwen3 VL 235B A22B Thinking
open sourceQwen model, released 23 Sept 2025.
$0.4
per 1M input tokens
$4.00
per 1M output tokens
—
per 1M cached-read tokens
Price history
input $/1M output $/1M7 Jul 2026 → 7 Aug 2026
Specifications
- Lab
- Qwen
- Released
- 23 Sept 2025
- Context window
- 131k tokens
- Max output
- 33k tokens
- Input modalities
- text, image
- Output modalities
- text
- Knowledge cutoff
- 2025-03-31
- Open source
- Yes
Benchmarks
| Benchmark | Category | Score | As of |
|---|---|---|---|
| LMArena (Chatbot Arena) | coding | 1427.4 (1413.1–1441.8) | 20 Jul 2026 |
| LMArena (Chatbot Arena) | overall | 1400.8 (1394.1–1407.6) | 20 Jul 2026 |
LMArena (Chatbot Arena) data © their authors, CC-BY-4.0
Frequently asked questions
How much does Qwen3 VL 235B A22B Thinking cost?
Qwen3 VL 235B A22B Thinking costs $0.4 per 1M input tokens and $4.00 per 1M output tokens (list price, updated every 6 hours).
What is Qwen3 VL 235B A22B Thinking's context window?
Qwen3 VL 235B A22B Thinking supports a 131k-token context window with up to 33k output tokens.