Qwen2.5-Coder-32B-Instruct vs Nova Lite 1.0
API pricing, benchmark indices and specs — updated 19 October 2026.
Qwen · A · Open weights
Params
32.8 B
Context
32,768
30d
546 K
apache-2.0 · commercial OK
amazon · B · API-only
Input / 1M
$0.06
Output / 1M
$0.24
AA index
6.7
proprietary · 300K context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-Coder-32B-Instruct | Nova Lite 1.0 |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 32.8 B | n/a — API-only |
| Architecture | Qwen2ForCausalLM | n/a — API-only |
| Context length | 32,768 | 300,000 |
| Licence | apache-2.0 | Proprietary |
| Commercial use | Allowed | Per API terms |
| Languages | 1 | n/a — API-only |
| Downloads 30d | 545,627 | n/a — API-only |
| Downloads all time | 13.7 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 | 2024-11-06 | n/a — API-only |
| API input price / 1M tokens | $0.66 | $0.06 |
| API output price / 1M tokens | $1.00 | $0.24 |
| Est. cost per 1M input + 1M output tokens | $1.66 | $0.30 |
| Cached input / 1M tokens | — | — |
| AA Intelligence Index | 6.7 | 6.7 |
| AA Coding Index | — | — |
| AA Agentic Index | — | — |
| Max output tokens | 29,491 | 5,120 |
| API providers | 1 | 1 |
| Tool calling | No | Yes |
| Reasoning mode | No | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen2.5-Coder-32B-Instruct
$1.66
Nova Lite 1.0
$0.30
Nova Lite 1.0 is 5.5× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-Coder-32B-Instruct · fp16
77.5 GB / 24 GB