Kimi-K3 vs Qwen3.8 Max (0902)
API pricing, benchmark indices and specs — updated 19 October 2026.
qwen · B · API-only
Input / 1M
$2.00
Output / 1M
$6.00
AA index
45.4
proprietary · 1M context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Kimi-K3 | Qwen3.8 Max (0902) |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 2,779.9 B | n/a — API-only |
| Architecture | KimiK3ForConditionalGeneration | n/a — API-only |
| Context length | 1,048,576 | 1,000,000 |
| Licence | other | Proprietary |
| Commercial use | Unknown | Per API terms |
| Languages | — | n/a — API-only |
| Downloads 30d | 922,082 | n/a — API-only |
| Downloads all time | 5.7 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 | 2026-06-13 | n/a — API-only |
| API input price / 1M tokens | $0.24 | $2.00 |
| API output price / 1M tokens | $10.80 | $6.00 |
| Est. cost per 1M input + 1M output tokens | $11.04 | $8.00 |
| Cached input / 1M tokens | $0.21 | $0.25 |
| AA Intelligence Index | 43.6 | 45.4 |
| AA Coding Index | 76.2 | 76.2 |
| AA Agentic Index | 50 | 56 |
| Max output tokens | 943,718 | 131,072 |
| API providers | 21 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Kimi-K3
$11.04
Qwen3.8 Max (0902)
$8.00
Qwen3.8 Max (0902) is 1.4× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Kimi-K3 · fp16
2,134.5 GB / 24 GB