Qwen3.5-35B-A3B vs o3
API pricing, benchmark indices and specs — updated 19 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.5-35B-A3B | o3 |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 36.0 B | n/a — API-only |
| Architecture | Qwen3_5MoeForConditionalGeneration | n/a — API-only |
| Context length | 262,144 | 200,000 |
| Licence | apache-2.0 | Proprietary |
| Commercial use | Allowed | Per API terms |
| Languages | — | n/a — API-only |
| Downloads 30d | 1,404,448 | n/a — API-only |
| Downloads all time | 20.8 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 | 2026-02-24 | n/a — API-only |
| API input price / 1M tokens | $0.14 | $2.00 |
| API output price / 1M tokens | $1.00 | $8.00 |
| Est. cost per 1M input + 1M output tokens | $1.14 | $10.00 |
| Cached input / 1M tokens | $0.05 | $0.50 |
| AA Intelligence Index | 19.3 | 20.2 |
| AA Coding Index | — | — |
| AA Agentic Index | — | — |
| Max output tokens | 81,920 | 100,000 |
| API providers | 7 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3.5-35B-A3B
$1.14
o3
$10.00
Qwen3.5-35B-A3B is 8.8× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.5-35B-A3B · fp16
85.0 GB / 24 GB