---
id: "qwen/qwen3-30b-a3b"
also: ["qwen/qwen3-30b-a3b-04-28", "Qwen/Qwen3-30B-A3B", "hf/Qwen/Qwen3-30B-A3B"]
cheapest_list_usd_per_m: "0.12 in, 0.5 out, at deepinfra/fp8 on openrouter"
cheapest_effective_usd_per_m: "0.1198 in, 0.4999 out, at deepinfra/fp8 on openrouter"
context: 40960
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", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p"]
endpoints: 3
gateways: "openrouter (2), hf (1)"
no_training: 2
trains: 0
retains_prompts: 1
---
# Qwen: Qwen3 30B A3B

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...