Qwen3.6-27B vs GPT-5.4 Nano
API pricing, benchmark indices and specs — updated 19 October 2026.
openai · B · API-only
Input / 1M
$0.20
Output / 1M
$1.25
AA index
20.7
proprietary · 400K context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-27B | GPT-5.4 Nano |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 27.8 B | n/a — API-only |
| Architecture | Qwen3_5ForConditionalGeneration | 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 | 2,363,950 | n/a — API-only |
| Downloads all time | 29.4 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 | 2026-04-21 | n/a — API-only |
| API input price / 1M tokens | $0.25 | $0.20 |
| API output price / 1M tokens | $2.00 | $1.25 |
| Est. cost per 1M input + 1M output tokens | $2.25 | $1.45 |
| Cached input / 1M tokens | $0.025 | $0.02 |
| AA Intelligence Index | 21.4 | 20.7 |
| AA Coding Index | 53.7 | 56.1 |
| AA Agentic Index | 18.5 | 16 |
| Max output tokens | 65,536 | 128,000 |
| API providers | 7 | 2 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3.6-27B
$2.25
GPT-5.4 Nano
$1.45
GPT-5.4 Nano is 1.6× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.6-27B · fp16
65.8 GB / 24 GB