Qwen3.5 397B A17B vs Qwen3.8 Max (0902)
Price, context window & benchmark comparison
VS
Compare different models
Verdict: Qwen3.5 397B A17B is 2.3× cheaper than Qwen3.8 Max (0902) on a typical 3:1 input/output mix. Qwen3.8 Max (0902) scores higher on the Artificial Analysis Intelligence Index (45.4 vs 18.4). Qwen3.8 Max (0902) has the larger context window (1M vs 262K).
| Qwen3.5 397B A17B | Qwen3.8 Max (0902) | |
|---|---|---|
| Input price / 1M | $0.55 | $2.00 |
| Output price / 1M | $3.50 | $6.00 |
| Blended price (3:1) | $1.29 | $3.00 |
| Cached input / 1M | $0.23 | $0.25 |
| Context window | 262K | 1M |
| Max output | 236K | 131K |
| Intelligence index | 18.4 | 45.4 |
| Coding index | 48.2 | 76.2 |
| Providers | — | 1 |
| Best provider uptime (30m) | — | 100.0% |
| Vision input | Yes | Yes |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Released | 2026-02-16 | 2026-09-03 |
| Retirement | — | — |
Cost calculator
FAQ
Which is cheaper, Qwen3.5 397B A17B or Qwen3.8 Max (0902)?
Qwen3.5 397B A17B is 2.3× cheaper than Qwen3.8 Max (0902) on a typical 3:1 input/output mix.
Qwen3.5 397B A17B vs Qwen3.8 Max (0902): which has a bigger context window?
Qwen3.5 397B A17B: 262,144 tokens. Qwen3.8 Max (0902): 1,000,000 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: Qwen3.5 397B A17B ≈ $2,850, Qwen3.8 Max (0902) ≈ $7,000.
More comparisons
Qwen3.5 397B A17B vs GLM 5.3 PrimeQwen3.5 397B A17B vs Qwen3.8 Max PrimeQwen3.5 397B A17B vs Command A+Qwen3.5 397B A17B vs GPT-6 Luna ProQwen3.5 397B A17B vs GPT-6 LunaQwen3.5 397B A17B vs GPT-6 Sol ProQwen3.5 397B A17B vs GPT-6 SolQwen3.5 397B A17B vs Claude Opus 5.5Qwen3.5 397B A17B vs MiMo-V2.6-Pro-UltraSpeedQwen3.5 397B A17B vs MiMo-V2.6-FlashQwen3.5 397B A17B vs Grok 4.7Qwen3.5 397B A17B vs Qwen3.8 Omni FlashQwen3.5 397B A17B vs GLM 5.3 FlashXQwen3.5 397B A17B vs DeepSeek V4.1 FlashQwen3.5 397B A17B vs GPT-6 AstraQwen3.5 397B A17B vs GPT-6 Astra ProQwen3.8 Max (0902) vs GLM 5.3 PrimeQwen3.8 Max (0902) vs Qwen3.8 Max PrimeQwen3.8 Max (0902) vs Command A+Qwen3.8 Max (0902) vs GPT-6 Luna ProQwen3.8 Max (0902) vs GPT-6 LunaQwen3.8 Max (0902) vs GPT-6 Sol ProQwen3.8 Max (0902) vs GPT-6 SolQwen3.8 Max (0902) vs Claude Opus 5.5