token.app › Compare › Qwen3 235B A22B vs Qwen3.8 Max
Qwen3 235B A22B vs Qwen3.8 Max
Qwen3.8 Max leads on 1 of 1 shared benchmarks. Qwen3 235B A22B is 3.8× cheaper per token on a blended 3:1 basis. Qwen3.8 Max accepts the larger context window (1M).
Head to head
Blended price uses a 3:1 input:output mix
| Qwen3 235B A22B | Qwen3.8 Max | |
|---|---|---|
| Provider | Alibaba | Alibaba |
| Input $/1M | $0.455 | $2.00 |
| Output $/1M | $1.82 | $6.00 |
| Blended $/1M | $0.796 | $3.00 |
| Context window | 131K | 1M |
| Max output | 8K | 131K |
| Released | Apr 2025 | Aug 2026 |
| Licence | Open weights | Proprietary |
| GPQA Diamond | 70.7% | 92.7% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Qwen3 235B A22B if…
- Costs less per token — $0.796 vs $3.00 blended
- Open weights — self-hostable
Choose Qwen3.8 Max if…
- Higher GPQA Diamond (92.7% vs 70.7%)
- Larger context window (1M)
- Newer model (released Aug 2026)
FAQ
Which is better, Qwen3 235B A22B or Qwen3.8 Max?
Across the 1 benchmark both models have independently-run scores for, Qwen3 235B A22B leads on 0 and Qwen3.8 Max leads on 1. Benchmarks are one input — price and context window are on this page too.
Is Qwen3 235B A22B cheaper than Qwen3.8 Max?
Qwen3 235B A22B is cheaper: $0.796 versus $3.00 per million tokens blended at 3:1 input:output. Input alone: $0.455 vs $2.00. Output alone: $1.82 vs $6.00.
What context windows do Qwen3 235B A22B and Qwen3.8 Max have?
Qwen3 235B A22B: 131,072 tokens. Qwen3.8 Max: 1,000,000 tokens.
Who makes Qwen3 235B A22B and Qwen3.8 Max?
Qwen3 235B A22B is made by Alibaba. Qwen3.8 Max is made by Alibaba.