Qwen: Qwen3.6 35B A3B
qwen/qwen3.6-35b-a3b
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
Modalities
In / Out Price
$0.15 / $1 per 1M
Context
262K
Released
Apr 27, 2026
Knowledge Cutoff
—
Providers
Different carriers host the same model. Reroute routes each request to the best one on price and uptime, and fails over to the next if a carrier goes down.
| Provider | Context | Input /M | Output /M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|---|
 Darkbloomfp4 | 262K | $0.05 | $0.70 | $0.025 | — | — | 100.00% |
 AkashMLfp8 | 262K | $0.10 | $0.90 | $0.05 | — | — | 100.00% |
 DeepInfrafp8 | 262K | $0.10 | $0.95 | $0.10 | — | — | 93.33% |
 DekaLLM | 262K | $0.10 | $1 | $0.05 | — | — | 100.00% |
 Venicefp8 | 256K | $0.10 | $1 | — | — | — | 100.00% |
 Parasailfp8 | 262K | $0.15 | $1 | $0.05 | — | — | 100.00% |
 AtlasCloudfp8 | 262K | $0.186 | $1.11 | $0.186 | — | — | 100.00% |
 Phala | 262K | $0.20 | $1.27 | $0.056 | — | — | 50.00% |
 SiliconFlowfp8 | 262K | $0.24 | $1.80 | $0.15 | — | — | 100.00% |
 CoreWeavefp8 | 262K | $0.25 | $1.25 | $0.25 | — | — | 100.00% |