Qwen: Qwen3.8 2.4T A95B
qwen/qwen3-8-2-4t-a95bQwen3.8 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 total.
Providers
5 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $2.00 | $6.00 | $0.25 | 1.94s | 33 tps | 100% | |
| $2.00 | $6.00 | $0.25 | 1.35s | 69 tps | 100% | |
| $2.00 | $6.00 | $0.25 | 5.66s | 34 tps | 99.73% | |
| $2.00 | $6.00 | $0.25 | 0.88s | 100 tps | 99.57% | |
 SiliconFlowfp8 | $2.00 | $6.00 | $0.25 | 3.69s | 34 tps | 99.13% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Qwen3.8 2.4T A95B in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Qwen3.8 2.4T A95B costs pay-as-you-go elsewhere, not what you pay here.
Performance
Time to first token and output speed across every provider, over the last 3 days.
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Apps
Tools that most often run Qwen3.8 2.4T A95B, by tokens this week.
Activity
196.6B tokens processed market-wide in the last month.
FAQ
Explore
Other models your pass can call.
