Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.15 |
| Output tokens | $1.00 |
Capabilities
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution
About Qwen3.6-35B-A3B
Qwen3.6-35B-A3B is an open-weight multimodal MoE model with 35B total parameters and 3B activated per token, released April 2026. It features a hybrid architecture combining Gated DeltaNet linear attention and standard Gated Attention with 256 total experts (8 routed + 1 shared), and includes a vision encoder for image and video understanding. Optimized for agentic coding, long-context reasoning, and visual tasks; supports 256K native context (extensible to ~1M via YaRN) with integrated thinking mode for multi-turn agent interactions.
Get Started
Model Specs
Released2026-04-16
Parameters35
Context262K
Architecturemoe