Qwen3.5-397B-A17B vs GPT-5 Mini
API pricing, benchmark indices and specs — updated 19 October 2026.
Qwen · A · Open weights
Params
403.4 B
Context
—
30d
667 K
apache-2.0 · commercial OK
openai · B · API-only
Input / 1M
$0.25
Output / 1M
$2.00
AA index
20.6
proprietary · 400K context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.5-397B-A17B | GPT-5 Mini |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 403.4 B | n/a — API-only |
| Architecture | Qwen3_5MoeForConditionalGeneration | n/a — API-only |
| Context length | 262,144 | 400,000 |
| Licence | apache-2.0 | Proprietary |
| Commercial use | Allowed | Per API terms |
| Languages | — | n/a — API-only |
| Downloads 30d | 667,204 | n/a — API-only |
| Downloads all time | 6.1 M | n/a — API-only |
| Quantizations on the Hub | SAFETENSORS | n/a — API-only |
| Gated | No | n/a — API-only |
| First seen on the Hub | 2026-02-16 | n/a — API-only |
| API input price / 1M tokens | $0.50 | $0.25 |
| API output price / 1M tokens | $3.60 | $2.00 |
| Est. cost per 1M input + 1M output tokens | $4.10 | $2.25 |
| Cached input / 1M tokens | $0.30 | $0.025 |
| AA Intelligence Index | 21.4 | 20.6 |
| AA Coding Index | — | — |
| AA Agentic Index | — | — |
| Max output tokens | 235,929 | 128,000 |
| API providers | 10 | 2 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3.5-397B-A17B
$4.10
GPT-5 Mini
$2.25
GPT-5 Mini is 1.8× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.5-397B-A17B · fp16
948.5 GB / 24 GB