---
id: "qwen/qwen3-32b"
also: ["qwen/qwen3-32b-04-28", "Qwen/Qwen3-32B", "hf/Qwen/Qwen3-32B", "requesty/alibaba/qwen3-32b"]
cheapest_list_usd_per_m: "0.08 in, 0.28 out, at deepinfra on hf"
cheapest_effective_usd_per_m: "0.0795 in, 0.2738 out, at deepinfra/fp8 on openrouter"
context: 131072
max_output: 16384
input: ["text"]
output: ["text"]
released: "2025-04-28"
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_a", "top_k", "top_logprobs", "top_p"]
endpoints: 10
gateways: "openrouter (5), hf (3), requesty (2)"
no_training: 7
trains: 0
retains_prompts: 0
coding: 15.3000
agentic: 0.9000
---
# Qwen: Qwen3 32B

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.