---
id: "qwen/qwen3-14b"
also: ["qwen/qwen3-14b-04-28", "Qwen/Qwen3-14B", "hf/Qwen/Qwen3-14B"]
cheapest_list_usd_per_m: "0.07 in, 0.2 out, at nscale on hf"
cheapest_effective_usd_per_m: "0.07 in, 0.2 out, at nscale on hf"
context: 40960
max_output: 36864
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_k", "top_logprobs", "top_p"]
endpoints: 6
gateways: "hf (3), openrouter (3)"
no_training: 3
trains: 0
retains_prompts: 1
coding: 13.8000
agentic: 0.9000
---
# Qwen: Qwen3 14B

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...