---
id: "qwen/qwen3.6-35b-a3b"
also: ["qwen/qwen3.6-35b-a3b-20260415", "Qwen/Qwen3.6-35B-A3B", "hf/Qwen/Qwen3.6-35B-A3B", "vercel/alibaba/qwen3.6-35b-a3b"]
cheapest_list_usd_per_m: "0.012 in, 0.11 out, at primeintellect/fp8 on openrouter"
cheapest_effective_usd_per_m: "0.0129 in, 0.1175 out, at primeintellect/fp8 on openrouter"
context: 262144
max_output: 235929
input: ["text", "image", "video"]
output: ["text"]
released: "2026-04-27"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 18
gateways: "openrouter (13), hf (3), vercel (2)"
no_training: 14
trains: 0
retains_prompts: 2
coding: 41.9000
agentic: 13.1000
---
# 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...