All Models

Qwen3.6 35B-A3B

qwen Reasoning Tool Calling Attachments Open Weights Structured Output

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...

Providers 15
Released Apr 1, 2026
Input Modalities text, image, video, audio
Output Modalities text
Tarsk Use coding

Available Providers (15)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Umans AI Coding Plan umans-qwen3.6-35b-a3b $0/MTok $0/MTok 262.1K 262.1K
NanoGPT qwen/Qwen3.6-35B-A3B $0.11/MTok $0.80/MTok 262.1K 16.4K
OpenRouter qwen/qwen3.6-35b-a3b $0.14/MTok $1/MTok 262.1K 262.1K
Hugging Face Qwen/Qwen3.6-35B-A3B $0.15/MTok $0.95/MTok 262.1K 65.5K
Deep Infra Qwen/Qwen3.6-35B-A3B $0.15/MTok $0.95/MTok 262.1K 81.9K
Wafer Qwen3.6-35B-A3B $0.15/MTok $1/MTok 256K 65.5K
Kilo Gateway qwen/qwen3.6-35b-a3b $0.16/MTok $0.97/MTok 262.1K 65.5K
SiliconFlow Qwen/Qwen3.6-35B-A3B $0.20/MTok $1.60/MTok 262.1K 262.1K
OrcaRouter qwen/qwen3.6-35b-a3b $0.25/MTok $1.49/MTok 262.1K 65.5K
LLM Gateway qwen3.6-35b-a3b $0.25/MTok $1.49/MTok 262.1K 65.5K
Alibaba qwen3.6-35b-a3b $0.25/MTok $1.49/MTok 262.1K 65.5K
Scaleway qwen3.6-35b-a3b $0.25/MTok $1.50/MTok 128K 16.4K
Neuralwatt Qwen/Qwen3.6-35B-A3B $0.29/MTok $1.15/MTok 131.1K 131.1K
evroc Qwen/Qwen3.6-35B-A3B-FP8 $0.34/MTok $1.38/MTok 262.1K 65.5K
LLMTR qwen3-6-35b $5/MTok $10/MTok 16.4K 65.5K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output