SPECS
| context window | 1,048,576 tokens |
|---|---|
| max output | 131,072 tokens |
| price in / out | $2 / $6 per 1M tokens |
| weights | open-weights |
openrouter.ai/api/v1/models (as of 2026-10-04)
MODEL / QWEN3-8-2-4T-A95B
Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion tot
model
textcodereasoning
Kindmodel
Access—
Pricing—
Free tier—
Caps3
PUBLISHED BENCHMARKS
| aaIndex | 39.9 |
|---|---|
| aaCodingIndex | 71.9 |
| aaAgenticIndex | 50.1 |
Artificial Analysis via OpenRouter · 2026-08
HUGGING FACE · LIVE
| pipeline | text-generation |
|---|---|
| parameters | 2446.2B |
| downloads | 33,969 |
| likes | 1282 |
| last modified | 2026-08-12 |
Qwen/Qwen3.8-2.4T-A95B · observed 2026-10-05 00:10:55
MACHINE-READABLE
GET /api/v1/resources/qwen3-8-2-4t-a95bOpen JSON ↗