Qwen: Qwen3.6 35B A3B
qwen/qwen3-6-35b-a3bQwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.
Providers
10 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.10 | $0.90 | $0.05 | 0.59s | 64 tps | 100% | |
| $0.15 | $1.00 | $0.05 | 0.53s | 98 tps | 100% | |
 CoreWeavefp8 | $0.25 | $1.25 | $0.25 | 0.44s | 133 tps | 99.94% |
| $0.10 | $1.00 | Variable | 0.94s | 93 tps | 99.89% | |
 Darkbloomfp4 | $0.05 | $0.70 | $0.03 | 1.62s | 56 tps | 99.47% |
 SiliconFlowfp8 | $0.24 | $1.80 | $0.15 | 0.83s | 54 tps | 99.37% |
| $0.10 | $1.00 | $0.05 | 0.48s | 147 tps | 98.59% | |
| $0.20 | $1.27 | $0.06 | 1.43s | 55 tps | 98.47% | |
 DeepInfraus · fp8 | $0.10 | $0.95 | $0.10 | 0.79s | 94 tps | 97.12% |
| $0.25 | $1.25 | $0.25 | 0.56s | 123 tps | 93.29% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Qwen3.6 35B A3B in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Qwen3.6 35B A3B 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 Qwen3.6 35B A3B, by tokens this week.
Activity
1215.9B tokens processed market-wide in the last month.
FAQ
Explore
Other models your pass can call.
