Qwen3-Coder-30B-A3B-Instruct vs Nova Premier 1.0
API pricing, benchmark indices and specs — updated 19 October 2026.
Qwen · A · Open weights
Params
30.5 B
Context
262,144
30d
629 K
apache-2.0 · commercial OK
amazon · B · API-only
Input / 1M
$2.50
Output / 1M
$12.50
AA index
9.2
proprietary · 1M context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-Coder-30B-A3B-Instruct | Nova Premier 1.0 |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 30.5 B | n/a — API-only |
| Architecture | Qwen3MoeForCausalLM | n/a — API-only |
| Context length | 262,144 | 1,000,000 |
| Licence | apache-2.0 | Proprietary |
| Commercial use | Allowed | Per API terms |
| Languages | — | n/a — API-only |
| Downloads 30d | 629,386 | n/a — API-only |
| Downloads all time | 15.9 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 | 2025-07-31 | n/a — API-only |
| API input price / 1M tokens | $0.07 | $2.50 |
| API output price / 1M tokens | $0.28 | $12.50 |
| Est. cost per 1M input + 1M output tokens | $0.35 | $15.00 |
| Cached input / 1M tokens | — | $0.63 |
| AA Intelligence Index | 9.6 | 9.2 |
| AA Coding Index | — | — |
| AA Agentic Index | — | — |
| Max output tokens | 235,929 | 32,000 |
| API providers | 2 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | No | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3-Coder-30B-A3B-Instruct
$0.35
Nova Premier 1.0
$15.00
Qwen3-Coder-30B-A3B-Instruct is 42.9× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-Coder-30B-A3B-Instruct · fp16 @ 256K ctx
214.2 GB / 24 GB