---
id: "qwen/qwen3-235b-a22b"
also: ["qwen/qwen3-235b-a22b-04-28", "Qwen/Qwen3-235B-A22B", "hf/Qwen/Qwen3-235B-A22B", "requesty/alibaba/qwen3-235b-a22b"]
cheapest_list_usd_per_m: "0.2 in, 0.6 out, at deepinfra on requesty"
cheapest_effective_usd_per_m: "0.2 in, 0.6 out, at deepinfra on requesty"
context: 131072
max_output: 8192
input: ["text"]
output: ["text"]
released: "2025-04-28"
params: ["frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p"]
endpoints: 6
gateways: "hf (3), requesty (2), openrouter (1)"
no_training: 3
trains: 0
retains_prompts: 1
intelligence: 9.5000
---
# Qwen: Qwen3 235B A22B

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.

Significantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.