The Qwen3.5 series 397B-A17B native vision-language model is based on a hybrid architecture design that integrates linear attention mechanisms with sparse Mixture-of-Experts (MoE), achieving higher inference efficiency.
function_callinghttps://api.novita.ai/v3/openai/v1/chat/completions| Model | Context | Max out | Pricing |
|---|---|---|---|
| Qwen3.5-Plus | 1M | 66K | — |
| Qwen3.5 35B A3B | 262K | 66K | $0.25$2 |
| Qwen3.5 27B | 262K | 66K | $0.3$2.4 |
| Qwen3.5 122B A10B | 262K | 66K | $0.4$3.2 |
| Qwen3.5 397B A17B | 262K | 66K | $0.6$3.6 |
/v1/models/novita/qwen/qwen3.5-397b-a17bThe Qwen3.5 series 397B-A17B native vision-language model is based on a hybrid architecture design that integrates linear attention mechanisms with sparse Mixture-of-Experts (MoE), achieving higher inference efficiency.