---
id: "qwen/qwen3.5-35b-a3b"
also: ["qwen/qwen3.5-35b-a3b-20260224", "Qwen/Qwen3.5-35B-A3B", "hf/Qwen/Qwen3.5-35B-A3B", "requesty/alibaba/qwen3.5-35b-a3b"]
cheapest_list_usd_per_m: "0.065 in, 0.75 out, at darkbloom/fp4 on openrouter"
cheapest_effective_usd_per_m: "0.065 in, 0.7497 out, at darkbloom/fp4 on openrouter"
context: 262144
max_output: 81920
input: ["text", "image", "video"]
output: ["text"]
released: "2026-02-25"
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: 12
gateways: "openrouter (9), hf (2), requesty (1)"
no_training: 10
trains: 0
retains_prompts: 3
coding: 37
---
# Qwen: Qwen3.5-35B-A3B

Qwen3.5-35B-A3B is an efficient Mixture-of-Experts model from Alibaba's Qwen3.5 series with 35B total parameters and only 3B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Delivers strong performance on reasoning, coding, and vision-language tasks at a fraction of the compute cost.