---
id: "qwen/qwen3-next-80b-a3b-instruct"
also: ["qwen/qwen3-next-80b-a3b-instruct-2509", "Qwen/Qwen3-Next-80B-A3B-Instruct", "hf/Qwen/Qwen3-Next-80B-A3B-Instruct", "vercel/alibaba/qwen3-next-80b-a3b-instruct"]
cheapest_list_usd_per_m: "0.072 in, 0.88 out, at deepinfra/fp8/flex on openrouter"
cheapest_effective_usd_per_m: "0.0719 in, 0.8777 out, at deepinfra/fp8/flex on openrouter"
context: 262144
max_output: 16384
input: ["text"]
output: ["text"]
released: "2025-09-11"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 15
gateways: "openrouter (7), vercel (5), hf (3)"
no_training: 11
trains: 0
retains_prompts: 2
---
# Qwen: Qwen3 Next 80B A3B Instruct

A new generation of open-source, non-thinking mode model powered by Qwen3. This version demonstrates superior Chinese text understanding, augmented logical reasoning, and enhanced capabilities in text generation tasks over the previous iteration (Qwen3-235B-A22B-Instruct-2507).