Qwen3-14B vs GPT-4
API pricing, benchmark indices and specs — updated 19 October 2026.
openai · B · API-only
Input / 1M
$30.00
Output / 1M
$60.00
AA index
6.7
proprietary · 8.2K context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-14B | GPT-4 |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 14.8 B | n/a — API-only |
| Architecture | Qwen3ForCausalLM | n/a — API-only |
| Context length | 40,960 | 8,191 |
| Licence | apache-2.0 | Proprietary |
| Commercial use | Allowed | Per API terms |
| Languages | — | n/a — API-only |
| Downloads 30d | 9,401,416 | n/a — API-only |
| Downloads all time | 38.0 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 | 2025-04-27 | n/a — API-only |
| API input price / 1M tokens | $0.12 | $30.00 |
| API output price / 1M tokens | $0.24 | $60.00 |
| Est. cost per 1M input + 1M output tokens | $0.36 | $90.00 |
| Cached input / 1M tokens | — | — |
| AA Intelligence Index | 6.7 | 6.7 |
| AA Coding Index | — | 13.1 |
| AA Agentic Index | — | — |
| Max output tokens | 16,384 | 4,096 |
| API providers | 2 | 2 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3-14B
$0.36
GPT-4
$90.00
Qwen3-14B is 250.0× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-14B · fp16
35.2 GB / 24 GB